Forensify
alexgreensh/repo-forensics
Cross-agent self-inspection of your AI-agent stack. An agent skill from alexgreensh/repo-forensics.
Conduct LINDDUN privacy threat modeling across all seven categories: Linking, Identifying, Non-repudiation, Detecting, Data Disclosure, Unawareness, and Non-compliance.
Install Linddun Threat Model
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill linddun-threat-model -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills linddun-threat-model --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/privacy/linddun-threat-model .claude/skills/linddun-threat-model && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "linddun-threat-model" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/linddun-threat-model into .claude/skills/linddun-threat-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linddun-threat-model", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/linddun-threat-modelType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill linddun-threat-model -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills linddun-threat-model --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/privacy/linddun-threat-model .agents/skills/linddun-threat-model && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "linddun-threat-model" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/linddun-threat-model into .agents/skills/linddun-threat-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linddun-threat-model", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill linddun-threat-model -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills linddun-threat-model --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/privacy/linddun-threat-model .cursor/skills/linddun-threat-model && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "linddun-threat-model" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/linddun-threat-model into .cursor/skills/linddun-threat-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linddun-threat-model", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/mukul975/Privacy-Data-Protection-Skills.git --path skills/privacy/linddun-threat-model--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill linddun-threat-model -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills linddun-threat-model --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/privacy/linddun-threat-model .gemini/skills/linddun-threat-model && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "linddun-threat-model" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/linddun-threat-model into .gemini/skills/linddun-threat-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linddun-threat-model", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install mukul975/Privacy-Data-Protection-Skills linddun-threat-modelInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill linddun-threat-model -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/privacy/linddun-threat-model .github/skills/linddun-threat-model && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "linddun-threat-model" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/linddun-threat-model into .github/skills/linddun-threat-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linddun-threat-model", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add mukul975/Privacy-Data-Protection-Skills --skill linddun-threat-model -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mukul975/Privacy-Data-Protection-Skills linddun-threat-model --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mukul975/Privacy-Data-Protection-Skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/privacy/linddun-threat-model .opencode/skills/linddun-threat-model && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "linddun-threat-model" agent skill from https://github.com/mukul975/Privacy-Data-Protection-Skills/tree/main/skills/privacy/linddun-threat-model into .opencode/skills/linddun-threat-model/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "linddun-threat-model", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
linddun-threat-model- GitHub stars
- 301
- Token cost
- ~3.2k tokens
- SKILL.md length
- 1,270 words
- Files
- 5 (incl. scripts, references, assets)
- Skills in repo
- 280
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Conduct LINDDUN privacy threat modeling across all seven categories: Linking, Identifying, Non-repudiation, Detecting, Data Disclosure, Unawareness, and Non-compliance.
- Works in 4 steps: Create Privacy-Annotated Data Flow Diagram → Map Threats to DFD Elements → Build Threat Trees → …
- Tasks that involve Threat modeling
- SKILL.md covers Overview, The Seven LINDDUN Threat…, DFD-Based Threat Analysis… and LINDDUN and STRIDE Integration, plus 2 more sections
- Runs Python scripts from its folder
What it does
Linddun Threat Model is an agent skill from mukul975/Privacy-Data-Protection-Skills. Conduct LINDDUN privacy threat modeling across all seven categories: Linking, Identifying, Non-repudiation, Detecting, Data Disclosure, Unawareness, and Non-compliance. Includes DFD-based analysis, threat trees, privacy-specific mitigation strategies, and integration with STRIDE security threat modeling.
Its SKILL.md is about 3.2k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts, reference files and assets (for example `assets/template.md`, `references/standards.md` and `references/workflows.md`).
It sits in Security, covering Threat modeling. The repository describes itself as: 282+ structured privacy & data protection skills for AI agents. GDPR, CCPA, EU AI Act, HIPAA, LGPD, PIPL, DPDP Act. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Threat modeling
Example prompts
- “/linddun-threat-model”
Requirements
- Python 3
Workflow steps
4 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 9b2ef9e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 1 file in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Linddun Threat Model loads about 3.2k tokens when it runs, and up to ~4.1k if it reads all its reference files. Until then it costs about 82 tokens; SKILL.md has 1,270 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from mukul975/Privacy-Data-Protection-Skills at commit 9b2ef9e, republished under its Apache-2.0 licence (© mukul975). 1,270 words, ~3,205 tokens.
Download SKILL.mdSave it as
.claude/skills/linddun-threat-model/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- linddun-threat-model
- description
- Conduct LINDDUN privacy threat modeling across all seven categories: Linking, Identifying, Non-repudiation, Detecting, Data Disclosure, Unawareness, and Non-compliance. Includes DFD-based analysis, threat trees, privacy-specific mitigation strategies, and integration with STRIDE security threat modeling.
- license
- Apache-2.0
- metadata.author
- mukul975
- metadata.version
- 1.0
- metadata.domain
- privacy
- metadata.subdomain
- privacy-engineering
- metadata.tags
- linddun, threat-modeling, privacy-threats, dfd-analysis, privacy-mitigation
LINDDUN Privacy Threat Modeling
Overview
LINDDUN is a systematic privacy threat modeling methodology developed by the DistriNet research group at KU Leuven. It provides a structured approach to identify and mitigate privacy threats in software systems. The acronym represents seven privacy threat categories that map to violations of privacy properties defined in ISO/IEC 29100.
The Seven LINDDUN Threat Categories
L — Linking
Definition: The ability to associate two or more data items or actions with an individual or group, beyond what is intended by the data subject.
Privacy Property Violated: Unlinkability
Threat Scenarios:
- Cross-referencing anonymized datasets to re-identify individuals
- Correlating browsing behavior across websites using fingerprinting
- Linking social media profiles to real identities through metadata
- Combining location data points to infer home/work addresses
Mitigation Strategies:
| Strategy | Technique | Implementation |
|---|---|---|
| Data minimization | Collect only necessary attributes | Review each data field against stated purpose |
| Pseudonymization | Replace identifiers with tokens | Use cryptographic pseudonymization with key separation |
| Mix networks | Obscure communication patterns | Route messages through anonymity networks |
| Aggregation | Present only group-level data | Enforce minimum group size (k>=5) for any query result |
| Session unlinkability | Prevent cross-session tracking | Rotate session tokens, avoid persistent identifiers |
I — Identifying
Definition: The ability to identify a data subject from a set of data items, connecting them to a known individual.
Privacy Property Violated: Anonymity
Threat Scenarios:
- Direct identification from unmasked PII in logs
- Quasi-identifier attacks (combining age, ZIP code, gender)
- Facial recognition from images in datasets
- Voice identification from audio recordings
- Writing style analysis (stylometry) in anonymous forums
Mitigation Strategies:
| Strategy | Technique | Implementation |
|---|---|---|
| Anonymization | Remove direct identifiers | Strip names, emails, SSNs before processing |
| k-Anonymity | Generalize quasi-identifiers | Ensure each record shares attributes with k-1 others |
| Differential privacy | Add calibrated noise | Apply epsilon-differential privacy to query responses |
| Data masking | Obscure identifying fields | Replace with realistic synthetic values |
| Access control | Restrict who can see raw data | Implement need-to-know access with purpose verification |
N — Non-repudiation
Definition: The inability of a data subject to deny having performed an action, even when such denial would be desirable for privacy.
Privacy Property Violated: Plausible deniability
Threat Scenarios:
- Immutable audit logs linking users to actions
- Digital signatures proving authorship of documents
- Non-repudiable transaction records
- Email delivery confirmations and read receipts
- Blockchain-based records that cannot be denied or deleted
Mitigation Strategies:
| Strategy | Technique | Implementation |
|---|---|---|
| Deniable encryption | Enable plausible deniability | Use deniable encryption schemes for sensitive data |
| Group signatures | Hide individual identity in group | Implement group signature schemes for authenticated actions |
| Minimal logging | Log only what is legally required | Review and minimize audit trail scope |
| Aggregate reporting | Report actions at group level | Aggregate activity reports rather than individual-level |
| Configurable receipts | Let users control acknowledgments | Allow opt-out of read receipts and delivery confirmations |
D — Detecting
Definition: The ability to determine whether a data subject has been involved in an action or is present in a dataset, even without identifying them specifically.
Privacy Property Violated: Undetectability
Threat Scenarios:
- Traffic analysis revealing communication patterns
- Database membership inference attacks
- Timing attacks revealing user activity
- Side-channel attacks revealing data access patterns
- Presence detection through network metadata
Mitigation Strategies:
| Strategy | Technique | Implementation |
|---|---|---|
| Traffic padding | Mask communication patterns | Generate dummy traffic to obscure real patterns |
| Steganography | Hide data within other data | Embed sensitive communications in innocuous content |
| Constant-time operations | Prevent timing analysis | Implement constant-time algorithms for sensitive operations |
| Oblivious RAM | Hide access patterns | Use ORAM protocols for privacy-critical data access |
| Differential privacy | Provide membership privacy | Apply differential privacy to prevent membership inference |
D — Data Disclosure
Definition: Unauthorized exposure of personal data to parties who should not have access.
Privacy Property Violated: Confidentiality
Threat Scenarios:
- SQL injection exposing database contents
- Misconfigured cloud storage buckets
- Insider threats with excessive access privileges
- Man-in-the-middle attacks on unencrypted channels
- API responses returning excessive data fields
- Backup media loss or theft
Mitigation Strategies:
| Strategy | Technique | Implementation |
|---|---|---|
| Encryption | Protect data at rest and in transit | AES-256 at rest, TLS 1.3 in transit |
| Access control | Enforce least privilege | RBAC with regular access reviews |
| Input validation | Prevent injection attacks | Parameterized queries, input sanitization |
| API field filtering | Return only requested fields | Implement field-level access control in APIs |
| DLP | Detect and prevent data exfiltration | Deploy DLP at network egress and endpoints |
U — Unawareness
Definition: Data subjects being insufficiently aware of data processing activities, their rights, or the consequences of providing or withholding data.
Privacy Property Violated: Transparency, Intervenability
Threat Scenarios:
- Hidden data collection through tracking pixels
- Opaque algorithmic decision-making
- Buried privacy policies with complex legal language
- Undisclosed data sharing with third parties
- Lack of notification when processing purposes change
- No mechanism for data subjects to exercise rights
Mitigation Strategies:
| Strategy | Technique | Implementation |
|---|---|---|
| Layered notices | Progressive disclosure | Short notice + full policy + just-in-time |
| Privacy dashboards | Centralized visibility | User-facing dashboard showing all data held |
| Consent management | Granular, informed consent | Purpose-specific consent with clear descriptions |
| Explainable AI | Algorithmic transparency | Provide meaningful explanations of automated decisions |
| Right facilitation | Easy rights exercise | Self-service portal for access, correction, deletion |
Show full SKILL.md (468 more words)Show less
N — Non-compliance
Definition: Processing personal data in ways that violate applicable laws, regulations, standards, or organizational policies.
Privacy Property Violated: Policy and consent compliance
Threat Scenarios:
- Processing without valid legal basis
- Failing to honor data subject rights within deadlines
- Cross-border transfers without adequate safeguards
- Retaining data beyond the stated retention period
- Processing children's data without parental consent
- Failing to conduct required impact assessments
Mitigation Strategies:
| Strategy | Technique | Implementation |
|---|---|---|
| Compliance mapping | Map processing to legal bases | Document legal basis per processing activity per jurisdiction |
| Automated enforcement | Technical compliance controls | Automated retention enforcement, consent verification |
| DPIA process | Impact assessment for high-risk processing | Mandatory DPIA before deploying new high-risk processing |
| Regulatory monitoring | Track legal developments | Subscribe to regulatory updates, conduct periodic gap analysis |
| Audit program | Verify ongoing compliance | Annual compliance audits with corrective action tracking |
DFD-Based Threat Analysis Process
Step 1: Create Privacy-Annotated Data Flow Diagram
[Data Subject] ---(personal data)--> [Web Application]
^ |
| v
[Notice] [Application Server]
|
+-------------+-------------+
| | |
v v v
[User Database] [Analytics DB] [Third-Party API]
(encrypted) (pseudonymized) (data sharing)Annotate each element with:
- Data types flowing through (PII categories)
- Trust boundaries crossed
- Storage locations and durations
- Processing purposes
- Access controls in place
Step 2: Map Threats to DFD Elements
| DFD Element | L | I | N | D(etect) | D(isclose) | U | N(on-comply) |
|---|---|---|---|---|---|---|---|
| Data flows | X | X | X | X | |||
| Data stores | X | X | X | X | |||
| Processes | X | X | X | X | X | X | X |
| External entities | X | X | X | X | X |
Step 3: Build Threat Trees
For each applicable threat category per DFD element, construct a threat tree:
Identifying Threat to User Database
├── Direct identifier exposure
│ ├── SQL injection reveals raw PII
│ ├── Backup media contains unencrypted PII
│ └── Admin access to production database
├── Quasi-identifier attack
│ ├── Combination of age + ZIP + gender
│ └── Temporal correlation of records
└── Inference attack
├── Aggregate query with small group size
└── Differential attack across query resultsStep 4: Prioritize and Mitigate
Use a risk matrix to prioritize identified threats:
| Likelihood / Impact | Negligible | Limited | Significant | Maximum |
|---|---|---|---|---|
| Very Likely | Medium | High | Critical | Critical |
| Likely | Low | Medium | High | Critical |
| Possible | Low | Medium | Medium | High |
| Unlikely | Low | Low | Medium | Medium |
| Rare | Low | Low | Low | Medium |
LINDDUN and STRIDE Integration
| LINDDUN Category | Related STRIDE Category | Overlap Area |
|---|---|---|
| Data Disclosure | Information Disclosure | Both address unauthorized data exposure |
| Non-compliance | Tampering | Integrity of consent records |
| Detecting | Information Disclosure | Metadata leakage |
| Identifying | Information Disclosure | PII exposure |
| Non-repudiation | Repudiation | Opposing perspectives on the same property |
Practical Application at Cipher Engineering Labs
Threat Modeling Workshop Agenda (4 hours)
- System Overview (30 min): Present the system architecture and data flows
- DFD Construction (45 min): Collaboratively build privacy-annotated DFD
- Threat Identification (90 min): Walk through each LINDDUN category per DFD element
- Prioritization (30 min): Score threats on risk matrix
- Mitigation Planning (45 min): Identify controls for high and critical risks
Deliverables
- Privacy-annotated Data Flow Diagram
- LINDDUN Threat Register (all identified threats with risk scores)
- Mitigation Plan (prioritized controls for high/critical threats)
- Residual Risk Statement
References
- Deng, M., Wuyts, K., Scandariato, R., Preneel, B., and Joosen, W. "A Privacy Threat Analysis Framework: Supporting the Elicitation and Fulfillment of Privacy Requirements." Requirements Engineering, 16(1):3-32, 2011.
- Wuyts, K. and Joosen, W. "LINDDUN Privacy Threat Modeling: A Tutorial." CW Reports, KU Leuven, 2015.
- LINDDUN GO — Lightweight approach: linddun.org
- ISO/IEC 29100:2011 — Information Technology — Security Techniques — Privacy Framework
- OWASP Privacy Risks Project
© mukul975, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts, references, assets) in skills/privacy/linddun-threat-model of mukul975/Privacy-Data-Protection-Skills.
- SKILL.md
- assets/template.md
- references/standards.md
- references/workflows.md
- scripts/process.py
Open the folder on GitHubat commit 9b2ef9e
Compare with similar skills
Linddun Threat Model next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Linddun Threat Model this skillmukul975/Privacy-Data-Protection-Skills | 301 | — | ~3.2k | Automated safety check: Pass | Apache-2.0 | |
| Forensifyalexgreensh/repo-forensics | 190 | — | ~2.5k | Automated safety check: Notes | Custom licence | |
| Create Rulecartography-cncf/cartography | 4.1k | — | ~3k | Automated safety check: Pass | Apache-2.0 | |
| Commit Security Scancodexstar69/bug-hunter | 520 | — | ~629 | Automated safety check: Pass | MIT | |
| Auditing Code For Vulnerabilitiestrilwu/secskills | 157 | — | ~3.2k | Automated safety check: Pass | MIT | |
| Threat Mitigation Mappingwshobson/agents | 40k | 8 repos | ~742 | Automated safety check: Pass | MIT |
Similar skills
Create Rule
cartography-cncf/cartography
Author a Cartography security rule (one or more Cypher Facts plus a Pydantic Finding output model) under cartography/rules/data/rules/.
Commit Security Scan
codexstar69/bug-hunter
Scan code changes for security vulnerabilities using Bug Hunter-native artifacts and STRIDE context.
Auditing Code For Vulnerabilities
trilwu/secskills
Audit source code for exploitable vulnerabilities using threat-model-driven review, taint tracing, invariant checking, and variant analysis.
Threat Mitigation Mapping
wshobson/agents
Match identified threats to preventive, detective and corrective controls across network, application, data, endpoint and process layers to plan remediation.
Audit Browser Security Boundaries
nordstjernen-web/northstar-browser
Audit browser-engine changes that process untrusted content or cross native-memory, origin, network, storage, extension, decoder, sandbox, or operating-system boundaries.
More from mukul975/Privacy-Data-Protection-Skills
All 280 skills in this repoAge Gating Services
mukul975/Privacy-Data-Protection-Skills
Implements age-gating mechanisms for online services to restrict access based on user age.
AI Data Retention
mukul975/Privacy-Data-Protection-Skills
Manages AI model retention and machine unlearning requirements.
AI Dpia
mukul975/Privacy-Data-Protection-Skills
Conducts Data Protection Impact Assessments for AI and ML systems per EDPB Guidelines 04/2025 on AI processing.
Dpia Mitigation Plan
mukul975/Privacy-Data-Protection-Skills
Structures risk mitigation planning and residual risk tracking for Data Protection Impact Assessments under GDPR Article 35(7)(d).
Gdpr Accountability
mukul975/Privacy-Data-Protection-Skills
Guides implementation of the GDPR accountability principle under Articles 5(2) and 24, including documentation requirements for policies, DPIAs, RoPA, training records, and breach logs.
Pia Threshold Screening
mukul975/Privacy-Data-Protection-Skills
Conducts pre-DPIA threshold screening to determine whether a full Data Protection Impact Assessment is required under GDPR Article 35.
Related
Categories
Questions about Linddun Threat Model
What does Linddun Threat Model do?
Conduct LINDDUN privacy threat modeling across all seven categories: Linking, Identifying, Non-repudiation, Detecting, Data Disclosure, Unawareness, and Non-compliance. Linddun Threat Model is an agent skill from mukul975/Privacy-Data-Protection-Skills. Conduct LINDDUN privacy threat modeling across all seven categories: Linking, Identifying, Non-repudiation, Detecting, Data Disclosure, Unawareness, and Non-compliance.
When should I use Linddun Threat Model?
Linddun Threat Model fits situations like: tasks that involve Threat modeling.
How do I install Linddun Threat Model in Claude Code?
Run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill linddun-threat-model -a claude-code`. Or copy the skill folder (skills/privacy/linddun-threat-model in mukul975/Privacy-Data-Protection-Skills) into .claude/skills/linddun-threat-model in your project. Claude Code loads it when a task matches its description.
How do I install Linddun Threat Model in Codex?
Run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill linddun-threat-model -a codex`. Or copy the skill folder (skills/privacy/linddun-threat-model in mukul975/Privacy-Data-Protection-Skills) into .agents/skills/linddun-threat-model in your project. Codex loads it when a task matches its description.
Can I use Linddun Threat Model in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mukul975/Privacy-Data-Protection-Skills --skill linddun-threat-model -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/linddun-threat-model, .gemini/skills/linddun-threat-model, .github/skills/linddun-threat-model and .opencode/skills/linddun-threat-model in your project.
What does Linddun Threat Model need to run?
Going by SKILL.md and its folder, Linddun Threat Model needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Linddun Threat Model access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Linddun Threat Model safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Linddun Threat Model use?
Linddun Threat Model is published under the Apache-2.0 licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Linddun Threat Model use?
About 3.2k tokens (SKILL.md is roughly 13k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 872 tokens, read only when the agent opens those files.
What are the alternatives to Linddun Threat Model?
Skills that share tags, products or a category with Linddun Threat Model: Forensify (alexgreensh/repo-forensics, 190 stars), Create Rule (cartography-cncf/cartography, 4.1k stars), Commit Security Scan (codexstar69/bug-hunter, 520 stars) and Auditing Code For Vulnerabilities (trilwu/secskills, 157 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Linddun Threat Model?
mukul975 (a GitHub user) maintains it in mukul975/Privacy-Data-Protection-Skills, which has 301 GitHub stars. The repository holds 280 skills in this directory. The repository was last updated on March 16, 2026.
Source: mukul975/Privacy-Data-Protection-Skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.