Deepsec Documentation Guide
vercel-labs/deepsec
Points the agent at deepsec's own docs to answer questions about initializing, configuring, resuming, scanning with and extending the vulnerability scanner.
Structured, adversarial, multi-phase security audit of a codebase — recon → coverage-led hunting → finder≠validator validation → machine-readable findings → target-neutral report
Install Security Audit
$ npx skills add alinaqi/maggy --skill security-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install alinaqi/maggy security-audit --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/alinaqi/maggy.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/security-audit .claude/skills/security-audit && 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 "security-audit" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/security-audit into .claude/skills/security-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-audit", 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/alinaqi/maggy/tree/main/skills/security-auditType 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 alinaqi/maggy --skill security-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install alinaqi/maggy security-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/security-audit .agents/skills/security-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "security-audit" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/security-audit into .agents/skills/security-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-audit", 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 alinaqi/maggy --skill security-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install alinaqi/maggy security-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/security-audit .cursor/skills/security-audit && 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 "security-audit" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/security-audit into .cursor/skills/security-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-audit", 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/alinaqi/maggy.git --path skills/security-audit--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 alinaqi/maggy --skill security-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install alinaqi/maggy security-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/security-audit .gemini/skills/security-audit && 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 "security-audit" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/security-audit into .gemini/skills/security-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-audit", 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 alinaqi/maggy security-auditInstalls 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 alinaqi/maggy --skill security-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/security-audit .github/skills/security-audit && 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 "security-audit" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/security-audit into .github/skills/security-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-audit", 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 alinaqi/maggy --skill security-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install alinaqi/maggy security-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/alinaqi/maggy.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/security-audit .opencode/skills/security-audit && 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 "security-audit" agent skill from https://github.com/alinaqi/maggy/tree/main/skills/security-audit into .opencode/skills/security-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "security-audit", 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
security-audit- GitHub stars
- 707
- Token cost
- ~1.6k tokens
- SKILL.md length
- 734 words
- Files
- 3
- Skills in repo
- 71
- Repo updated
- First seen
- Licence
- MIT
At a glance
Structured, adversarial, multi-phase security audit of a codebase — recon → coverage-led hunting → finder≠validator validation → machine-readable findings → target-neutral report
- Works in 6 steps: Reconnaissance → architecture.md +… → Coverage-led hunting → Adversarial validation (finder ≠… → …
- Tasks that involve Security review
- SKILL.md covers Principles (read first), Phases, Anti-patterns and How it fits the harness
- Runs Python scripts from its folder; calls python3
What it does
Security Audit is an agent skill from alinaqi/maggy. Structured, adversarial, multi-phase security audit of a codebase — recon → coverage-led hunting → finder≠validator validation → machine-readable findings → target-neutral report
Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `report-schema.json` and `validate_findings.py`).
It sits in Security, covering Security review. The repository describes itself as: What started as an opinionated Claude Code setup kit is now an autonomous AI engineering command center. The licence is MIT.
When your agent uses it
- Tasks that involve Security review
Example prompts
- “/security-audit”
Requirements
- Python 3
- Pre-approved tools (allowed-tools): Read, Glob, Grep, Bash, Task
Workflow steps
6 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 72a456e. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
ReadGlobGrepBashTask
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships script files (Python), which the agent can run.
Shell commands in SKILL.md call:
python3
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
Security Audit loads about 1.6k tokens when it runs. Until then it costs about 48 tokens; SKILL.md has 734 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: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Read, Glob, Grep, Bash, Task
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); files beside SKILL.md are not scanned.
SKILL.md
The full file from alinaqi/maggy at commit 72a456e, republished under its MIT licence (© alinaqi). 734 words, ~1,599 tokens.
Download SKILL.mdSave it as
.claude/skills/security-audit/SKILL.md (or your agent's skills folder). This skill also uses 2 other files; get the full folder from GitHub.- name
- security-audit
- description
- Structured, adversarial, multi-phase security audit of a codebase — recon → coverage-led hunting → finder≠validator validation → machine-readable findings → target-neutral report
- allowed-tools
- Read, Glob, Grep, Bash, Task
- when-to-use
- When asked to "security audit", "find vulnerabilities", "pen-test the code", or audit a codebase/PR for security before a release. For preventive coding…
- user-invocable
- true
- effort
- high
Security Audit — adversarial, evidence-grounded
A full audit, not a checklist. It runs in phases, keeps a coverage ledger so
nothing is skipped silently, and — the core discipline — the agent that finds a
candidate is never the one that confirms it. Severity is likelihood × impact,
not deviation from a style rule. Output is machine-readable and reproducible.
Methodology inspired by Cloudflare's public security-audit-skill, rebuilt to reuse maggy's own pieces:
council-reviewfor adversarial validation,cpg-analysis(Joern/CodeQL) for static taint/data-flow,agent-teams/polyphonyfor isolated parallel hunters, andsecurityfor the vuln classes.
Principles (read first)
- Evidence over intuition. A finding is
confirmedonly when you can name the file:line of the boundary that fails and a concrete attack that crosses it. - Finder ≠ validator. Whoever proposes a candidate must not confirm it. A
different agent (or a
council-reviewmodel) tries to disprove it. - Impact-driven severity. Rate
likelihood × impact, not "differs from best practice". A hardcoded key in a test fixture is not critical; an auth bypass on a tenant boundary is. - Coverage is tracked, not assumed. Every input surface / trust boundary is a ledger unit with a status; a coverage critic hunts the gaps.
- No theater. Do not pad the report with generic "consider using HTTPS" advice. Report only boundary failures you can stand behind.
Phases
1. Reconnaissance → architecture.md + coverage-ledger.json
Map the target before hunting. Identify: entry points (HTTP routes, CLI, queue
consumers, webhooks), trust boundaries (authn/authz, tenant isolation, privilege
transitions), input surfaces (params, headers, files, env, deserialization),
secret handling, external calls (SSRF surface), and data stores. Write a short
architecture.md, then enumerate every surface as a unit in
coverage-ledger.json ({id, surface, boundary, status: pending}).
2. Coverage-led hunting
For each ledger unit, hunt the relevant classes. Prefer isolated sub-agents
(via agent-teams / polyphony) so one hunter's context does not bias another,
and lean on cpg-analysis for data-flow/taint where a graph beats grep. Mark each
unit hunted; a coverage critic pass re-reads the ledger and reopens units
that were skimmed. Classes to cover (depth in security + cpg-analysis):
| Class | Look for |
|---|---|
| Injection | SQL/NoSQL/OS/LDAP/template; unparameterized queries, shell=True, eval |
| AuthN / AuthZ | missing checks, IDOR, broken tenant isolation, JWT/session flaws |
| Secrets | keys in code/history/logs, client-exposed VITE_/NEXT_PUBLIC_ secrets |
| SSRF / egress | user-controlled URLs, metadata endpoints, unvalidated redirects |
| Deserialization | pickle/yaml.load/Marshal on untrusted input |
| Path / file | traversal, arbitrary write, zip-slip, unsafe temp files |
| LLM / prompt | prompt injection, tool-abuse, unbounded fan-out, data exfil via output |
| Supply chain | typosquats, unpinned deps, postinstall scripts, CI token scope |
| Cloud / IaC | over-broad IAM, public buckets, exposed admin, secrets in env |
| Client-side | XSS, DOM sinks, CSP gaps, sensitive data in localStorage |
| Resource / DoS | unbounded loops/allocations, regex catastrophic backtracking |
| Data isolation | cross-tenant reads, missing RLS, PII in logs/caches |
| Memory (native) | overflow, UAF, integer wrap (for C/C++/unsafe Rust targets) |
Show full SKILL.md (288 more words)Show less
3. Adversarial validation (finder ≠ validator)
For each unique candidate, a different reviewer attempts to disprove it:
is the tainted input actually reachable? is there a guard upstream? is the sink
real? Route this through council-review (multiple models vote) for anything
rated high/critical. Assign a verdict: confirmed, needs_validation, or
rejected.
4. Structured output → findings.json
Emit findings.json conforming to report-schema.json (shipped in this skill).
Validate it before reporting:
python3 "$(cat ~/.claude/.bootstrap-dir)/skills/security-audit/validate_findings.py" findings.jsonThe validator enforces the rules that keep the audit honest: unique ids, valid
enums, and that every confirmed finding has a file:line location, an attack
scenario, and a validated_by that differs from found_by.
5. Record verification
A fresh agent re-opens each confirmed finding and checks the cited file:line
still supports the claim (code may have moved). A material mismatch drops it
back to needs_validation.
6. Target-neutral report → REPORT.md
Write REPORT.md (executive summary + confirmed findings by severity),
FINDINGS-DETAIL.md (per-finding evidence + remediation), and
NEEDS-VALIDATION.md (candidates that could not be confirmed). Neutral tone: no
vendor names, no editorializing, just boundary → attack → impact → fix.
Anti-patterns
- Confirming a finding you found yourself without an independent disprove attempt.
- Severity inflation ("uses md5" rated critical with no reachable attack).
- Grep-only hunting on a data-flow bug — use
cpg-analysis. - A report that lists advice instead of reachable, evidence-backed findings.
- Running audited target code outside a sandbox. Read and analyze; never execute untrusted target code to "see what it does".
How it fits the harness
- Slots into the
baseDefinition of Done for security-critical changes as the "prove it's safe" gate, above the preventivesecurityskill. - Reuses
council-review(adversarial validation),cpg-analysis(static taint),agent-teams/polyphony(isolated parallel hunters). - Iterations are additive: a second run over the same ledger typically surfaces more, so re-run before a major release rather than trusting one pass.
© alinaqi, MIT. 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 2 other files in skills/security-audit of alinaqi/maggy.
- SKILL.md
- report-schema.json
- validate_findings.py
Open the folder on GitHubat commit 72a456e
Compare with similar skills
Security Audit 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 |
|---|---|---|---|---|---|---|
| Security Audit this skillalinaqi/maggy | 707 | — | ~1.6k | Automated safety check: Notes | MIT | |
| Deepsec Documentation Guidevercel-labs/deepsec | 8.1k | — | ~956 | Automated safety check: Pass | Apache-2.0 | |
| Kubernetes Network Security Auditkubeshark/kubeshark | 12k | — | ~7.3k | Automated safety check: Notes | Apache-2.0 | |
| Native Dependency Updatemono/SkiaSharp | 5.6k | — | ~4.1k | Automated safety check: Pass | MIT | |
| Semgrep Security Scantrailofbits/skills | 7.4k | — | ~3.7k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| Skillward AuditFangcun-AI/SkillWard | 143 | — | ~2.9k | Automated safety check: Pass | Custom licence |
Similar skills
- Official
Kubernetes Network Security Audit
kubeshark/kubeshark
Hunts for compromised workloads and malicious traffic in a Kubernetes cluster by sweeping network data through Kubeshark MCP, mapped to MITRE ATT&CK.
Native Dependency Update
mono/SkiaSharp
Update native dependencies (libpng, libexpat, zlib, libwebp, harfbuzz, freetype, libjpeg-turbo, etc.) in SkiaSharp's Skia fork.
- Official
Semgrep Security Scan
trailofbits/skills
Detects languages, proposes rulesets for approval, then runs the approved Semgrep scan across a codebase and merges the output into one SARIF file.
Skillward Audit
Fangcun-AI/SkillWard
Security-audit a third-party skill bundle (folder with SKILL.md, or .zip / .tar.gz archive) before installing it, using the SkillWard cloud scanner.
Security Audit
TheDecipherist/claude-code-mastery
Checks a codebase for hardcoded secrets, vulnerable dependencies, weak input handling, weak authentication and unsafe transport settings before deployment or merge.
More from alinaqi/maggy
All 71 skills in this repoAeo Optimization
alinaqi/maggy
AI Engine Optimization - semantic triples, page templates, content clusters for AI citations
Agent Teams
alinaqi/maggy
Claude Code Agent Teams - default team-based development with strict TDD pipeline enforcement
AI Models
alinaqi/maggy
Latest AI models reference - Claude, OpenAI, Gemini, Eleven Labs, Replicate
Android Java
alinaqi/maggy
Android Java development with MVVM, ViewBinding, and Espresso testing
Android Kotlin
alinaqi/maggy
Android Kotlin development with Coroutines, Jetpack Compose, Hilt, and MockK testing
Autonomous Testing
alinaqi/maggy
AI-driven testing agent that auto-discovers, generates, executes, evaluates, and fixes tests for any project type
Related
Categories
Questions about Security Audit
What does Security Audit do?
Structured, adversarial, multi-phase security audit of a codebase — recon → coverage-led hunting → finder≠validator validation → machine-readable findings → target-neutral report. Security Audit is an agent skill from alinaqi/maggy.
When should I use Security Audit?
Security Audit fits situations like: tasks that involve Security review.
How do I install Security Audit in Claude Code?
Run `npx skills add alinaqi/maggy --skill security-audit -a claude-code`. Or copy the skill folder (skills/security-audit in alinaqi/maggy) into .claude/skills/security-audit in your project. Claude Code loads it when a task matches its description.
How do I install Security Audit in Codex?
Run `npx skills add alinaqi/maggy --skill security-audit -a codex`. Or copy the skill folder (skills/security-audit in alinaqi/maggy) into .agents/skills/security-audit in your project. Codex loads it when a task matches its description.
Can I use Security Audit 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 alinaqi/maggy --skill security-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/security-audit, .gemini/skills/security-audit, .github/skills/security-audit and .opencode/skills/security-audit in your project.
What does Security Audit need to run?
Going by SKILL.md and its folder, Security Audit needs Python for the scripts in its folder and the command-line tools its instructions call (python3). Our summary lists: Python 3. Its frontmatter pre-approves these tools: Read, Glob, Grep, Bash, Task.
Does Security Audit 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 Security Audit safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Security Audit use?
Security Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Security Audit use?
About 1.6k tokens (SKILL.md is roughly 6.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Security Audit?
Skills that share tags, products or a category with Security Audit: Deepsec Documentation Guide (vercel-labs/deepsec, 8.1k stars), Kubernetes Network Security Audit (kubeshark/kubeshark, 12k stars), Native Dependency Update (mono/SkiaSharp, 5.6k stars) and Semgrep Security Scan (trailofbits/skills, 7.4k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Security Audit?
alinaqi (a GitHub user) maintains it in alinaqi/maggy, which has 707 GitHub stars. The repository holds 71 skills in this directory. The repository was last updated on September 24, 2026.
Source: alinaqi/maggy on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.