Semgrep
vigolium/piolium
Run Semgrep static analysis scan on a codebase using parallel subagents.
Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits.
Install Operate Sast Toolchain
$ npx skills add cyberful/cyberful --skill operate-sast-toolchain -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cyberful/cyberful operate-sast-toolchain --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/cyberful/cyberful.git skills-src && mkdir -p .claude/skills && cp -r skills-src/cyberful/builtin/skills/operate-sast-toolchain .claude/skills/operate-sast-toolchain && 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 "operate-sast-toolchain" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-sast-toolchain into .claude/skills/operate-sast-toolchain/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-sast-toolchain", 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/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-sast-toolchainType 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 cyberful/cyberful --skill operate-sast-toolchain -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cyberful/cyberful operate-sast-toolchain --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .agents/skills && cp -r skills-src/cyberful/builtin/skills/operate-sast-toolchain .agents/skills/operate-sast-toolchain && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "operate-sast-toolchain" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-sast-toolchain into .agents/skills/operate-sast-toolchain/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-sast-toolchain", 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 cyberful/cyberful --skill operate-sast-toolchain -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cyberful/cyberful operate-sast-toolchain --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/cyberful/builtin/skills/operate-sast-toolchain .cursor/skills/operate-sast-toolchain && 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 "operate-sast-toolchain" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-sast-toolchain into .cursor/skills/operate-sast-toolchain/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-sast-toolchain", 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/cyberful/cyberful.git --path cyberful/builtin/skills/operate-sast-toolchain--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 cyberful/cyberful --skill operate-sast-toolchain -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cyberful/cyberful operate-sast-toolchain --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/cyberful/builtin/skills/operate-sast-toolchain .gemini/skills/operate-sast-toolchain && 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 "operate-sast-toolchain" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-sast-toolchain into .gemini/skills/operate-sast-toolchain/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-sast-toolchain", 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 cyberful/cyberful operate-sast-toolchainInstalls 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 cyberful/cyberful --skill operate-sast-toolchain -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .github/skills && cp -r skills-src/cyberful/builtin/skills/operate-sast-toolchain .github/skills/operate-sast-toolchain && 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 "operate-sast-toolchain" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-sast-toolchain into .github/skills/operate-sast-toolchain/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-sast-toolchain", 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 cyberful/cyberful --skill operate-sast-toolchain -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cyberful/cyberful operate-sast-toolchain --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cyberful/cyberful.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/cyberful/builtin/skills/operate-sast-toolchain .opencode/skills/operate-sast-toolchain && 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 "operate-sast-toolchain" agent skill from https://github.com/cyberful/cyberful/tree/main/cyberful/builtin/skills/operate-sast-toolchain into .opencode/skills/operate-sast-toolchain/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "operate-sast-toolchain", 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
operate-sast-toolchain- GitHub stars
- 135
- Token cost
- ~1.3k tokens
- SKILL.md length
- 522 words
- Files
- 9 (incl. scripts, references, assets)
- Skills in repo
- 85
- Repo updated
- First seen
- Licence
- AGPL-3.0
At a glance
Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits.
- Works in 5 steps: Syntax anchors: dangerous APIs, control… → Project abstractions: wrappers,… → Local taint: untrusted sources to sinks… → …
- Repository baselining
- SKILL.md covers Build the scan manifest, Layer the rules, Run reproducibly and Validate every custom rule, plus 2 more sections
- Runs Python scripts from its folder
What it does
Operate Sast Toolchain is an agent skill from cyberful/cyberful. Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits. Use for repository baselining, custom rule authoring, taint/dataflow searches, framework-specific sink discovery, variant analysis, diff review, scanner reconciliation, SARIF production, or when generic rules miss project-specific security invariants.
Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 13 other files, including scripts, reference files and assets (for example `agents/openai.yaml`, `assets/sast-campaign.example.json` and `assets/sast-campaign.schema.json`).
It sits in Security, covering Static analysis and SAST. It works with Semgrep. The repository describes itself as: Cyberful is an open-source AI Red Team for discovering, exploiting, verifying, and remediating vulnerabilities. The licence is AGPL-3.0.
When your agent uses it
- Repository baselining
- Custom rule authoring
- Taint/dataflow searches
- Framework-specific sink discovery
Example prompts
- “/operate-sast-toolchain”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Syntax anchors: dangerous APIs, control definitions, route handlers, deserializers, loaders, process/network/file sinks.
- Project abstractions: wrappers, builders, helper methods, middleware, decorators, policy functions, generated clients.
- Local taint: untrusted sources to sinks with sanitizers and propagators.
- Security invariants: privileged operation without required dominating check, tenant identifier replaced downstream, unsafe fallback…
- Variants: generalize a confirmed bug by semantic mechanism, not copied token.
What it can do on your machine
Read from SKILL.md and the folder at commit ec598a6. 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 2 files 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
Operate Sast Toolchain loads about 1.3k tokens when it runs, and up to ~2.2k if it reads all its reference files. Until then it costs about 101 tokens; SKILL.md has 522 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 cyberful/cyberful at commit ec598a6, republished under its AGPL-3.0 licence (© cyberful). 522 words, ~1,286 tokens.
Download SKILL.mdSave it as
.claude/skills/operate-sast-toolchain/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.- name
- operate-sast-toolchain
- description
- Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits. Use for repository baselining, custom rule authoring, taint/dataflow searches, framework-specific sink discovery, variant analysis, diff review, scanner reconciliation, SARIF production, or when generic rules miss project-specific security invariants.
- metadata.domain
- security-tooling
- metadata.subdomain
- static-application-security-testing
- metadata.triggers
- SAST campaign, Semgrep security scan, custom static analysis rule, SARIF source analysis, static analysis coverage
- metadata.tags
- SAST, Semgrep, SARIF, taint-analysis, source-code, variant-analysis
Operate SAST Toolchain
Use static analysis to index risk and scale a known reasoning pattern. A finding becomes meaningful only after reachability, data/control flow, authority, and runtime configuration are established.
Build the scan manifest
Record commit, languages, parsers, generated/vendor/build directories, submodules, ignored files, file counts/bytes by language, ruleset identity/hash, Semgrep version, command, timeout, memory, and parse errors.
Run a parser/coverage pass before a security pass. A clean result over 40% of the security-relevant source is not a clean repository.
Layer the rules
- Syntax anchors: dangerous APIs, control definitions, route handlers, deserializers, loaders, process/network/file sinks.
- Project abstractions: wrappers, builders, helper methods, middleware, decorators, policy functions, generated clients.
- Local taint: untrusted sources to sinks with sanitizers and propagators.
- Security invariants: privileged operation without required dominating check, tenant identifier replaced downstream, unsafe fallback, missing state transition.
- Variants: generalize a confirmed bug by semantic mechanism, not copied token.
Read references/semgrep-fieldbook.md when designing rules or interpreting coverage.
Run reproducibly
Use the dedicated semgrep tool with:
- scan subcommand;
- local pinned rule files/directories;
- --metrics=off;
- explicit target roots and excludes;
- JSON or SARIF output under the workarea;
- controlled jobs, timeout, max-target-bytes, and error behavior.
Keep broad discovery output separate from release-gating output. Baselines suppress historical results for triage; they do not prove historical code safe.
For repeatable execution, stage scripts/run_sast_campaign.py, its manifest, and the campaign example. The orchestrator accepts only local rules and explicitly authorized workspace roots, forces metrics off, uses bounded jobs and timeouts, and preserves raw JSON and stderr under the evidence schema. Interpret reachability and exploitability after the campaign; the script deliberately does not normalize findings.
For C/C++, use native_static_analysis import_compile_db before compiler-aware checks when a compile database exists. Pass run_checks only a C/C++ source file or a directory containing C/C++ sources; ELF and other non-source inputs return a structured unsupported result without invoking source analyzers and belong in the binary-analysis workflow. Use run_checks, trace_source_sink, and inspect_variadic_calls as bounded discovery passes, then validate with the actual build flags, Clang-Tidy/scan-build output, and complete source context. Generate a compile database with Bear only inside a mutable lab copy.
Show full SKILL.md (176 more words)Show less
Validate every custom rule
Create minimal positive, negative, near-miss, and sanitizer fixtures. Include aliasing, wrapper, alternate syntax, async/callback, and language-version cases relevant to the repository. Run the rule against fixtures before the product tree.
For each match:
- locate production entry point;
- trace values and authority across wrappers and storage;
- identify dominating validation/authorization;
- inspect configuration and dependency behavior;
- classify reachability and effect;
- search for siblings from both source and sink directions.
Diagnose negatives
A zero-match rule may mean:
- wrong language/parser;
- files excluded or too large;
- syntactic shape differs;
- wrapper hides source/sink;
- interfile/interprocedural flow exceeds the engine model;
- sanitizer definition over-matches;
- framework generated code owns the path;
- data is stored and consumed in another process;
- runtime reflection or dynamic dispatch defeats static resolution.
Use search, call hierarchy, runtime tests, and manual tracing to close these gaps.
Deliver
Preserve scan manifest, raw output, parse/timeout/errors, rules and tests, triage decisions, confirmed paths, rejected matches, coverage ledger, and systemic variants. A suppression must state whether it is unreachable, controlled, accepted, duplicate, test-only, or scanner limitation.
© cyberful, AGPL-3.0. 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 8 other files (scripts, references, assets) in cyberful/builtin/skills/operate-sast-toolchain of cyberful/cyberful.
- SKILL.md
- agents/openai.yaml
- assets/sast-campaign.example.json
- assets/sast-campaign.schema.json
- assets/sast-evidence.schema.json
- references/semgrep-fieldbook.md
- scripts/manifest.json
- scripts/run_sast_campaign.py
- tests/test_run_sast_campaign.py
Open the folder on GitHubat commit ec598a6
Compare with similar skills
Operate Sast Toolchain 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 |
|---|---|---|---|---|---|---|
| Operate Sast Toolchain this skillcyberful/cyberful | 135 | — | ~1.3k | Automated safety check: Pass | AGPL-3.0 | |
| Semgrepvigolium/piolium | 140 | 1 repos | ~2.4k | Automated safety check: Notes | MIT | |
| Semgrep Security Scantrailofbits/skills | 7.5k | — | ~3.7k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| Sast SemgrepAgentSecOps/SecOpsAgentKit | 220 | 2 repos | ~2.4k | Automated safety check: Pass | Custom licence | |
| Semgrep Rule Creatortrailofbits/skills | 7.5k | 6 repos | ~1.8k | Automated safety check: Notes | CC-BY-SA-4.0 | |
| Semgrep Rule Variant Creatortrailofbits/skills | 7.5k | 5 repos | ~3.4k | Automated safety check: Notes | CC-BY-SA-4.0 |
Similar skills
- 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.
Sast Semgrep
AgentSecOps/SecOpsAgentKit
Static application security testing (SAST) using Semgrep for vulnerability detection, security code review, and secure coding guidance with OWASP and CWE framework mapping.
- Official
Semgrep Rule Creator
trailofbits/skills
Creates custom Semgrep rules for detecting security vulnerabilities, bug patterns, and code patterns.
- Official
Semgrep Rule Variant Creator
trailofbits/skills
Creates language variants of existing Semgrep rules. An agent skill from trailofbits/skills.
Semgrep
waybarrios/opencode-power-pack
Run Semgrep static analysis across a codebase, optionally using Semgrep Pro for cross-file taint analysis.
More from cyberful/cyberful
All 85 skills in this repoAudit Infrastructure As Code
cyberful/cyberful
Audit infrastructure-as-code artifacts for unsafe defaults, policy gaps, privilege exposure, control drift, and deployment-impact evidence.
Audit Kubernetes Policy Enforcement
cyberful/cyberful
Audit Kubernetes admission and policy-as-code enforcement against local workload manifests, exception paths, namespace scope, and deployment evidence.
Audit Pci Dss Penetration Test Evidence
cyberful/cyberful
Audit PCI DSS penetration-test methodology, scope, internal and external reports, segmentation results, tester independence, remediation, retesting, retention, and multi-tenant support evidence.
Operate Content Discovery
cyberful/cyberful
Design and interpret advanced content discovery with ffuf and complementary web fuzzers.
Operate Network Recon
cyberful/cyberful
Build a high-fidelity network and service inventory using Nmap, Masscan, packet capture, DNS, and protocol-specific follow-up.
Operate Supply Chain Toolchain
cyberful/cyberful
Operate Syft, Grype, Trivy, Gitleaks, Retire.js, package-manager metadata, and build evidence for advanced software-supply-chain assessment.
Related
Works with
Categories
Questions about Operate Sast Toolchain
What does Operate Sast Toolchain do?
Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits. Operate Sast Toolchain is an agent skill from cyberful/cyberful. Operate Semgrep and source-oriented static analysis as a hypothesis, coverage, and regression system during advanced code audits.
When should I use Operate Sast Toolchain?
Operate Sast Toolchain fits situations like: repository baselining; custom rule authoring; taint/dataflow searches; framework-specific sink discovery.
How do I install Operate Sast Toolchain in Claude Code?
Run `npx skills add cyberful/cyberful --skill operate-sast-toolchain -a claude-code`. Or copy the skill folder (cyberful/builtin/skills/operate-sast-toolchain in cyberful/cyberful) into .claude/skills/operate-sast-toolchain in your project. Claude Code loads it when a task matches its description.
How do I install Operate Sast Toolchain in Codex?
Run `npx skills add cyberful/cyberful --skill operate-sast-toolchain -a codex`. Or copy the skill folder (cyberful/builtin/skills/operate-sast-toolchain in cyberful/cyberful) into .agents/skills/operate-sast-toolchain in your project. Codex loads it when a task matches its description.
Can I use Operate Sast Toolchain 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 cyberful/cyberful --skill operate-sast-toolchain -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/operate-sast-toolchain, .gemini/skills/operate-sast-toolchain, .github/skills/operate-sast-toolchain and .opencode/skills/operate-sast-toolchain in your project.
What does Operate Sast Toolchain need to run?
Going by SKILL.md and its folder, Operate Sast Toolchain needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Operate Sast Toolchain 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 Operate Sast Toolchain 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 Operate Sast Toolchain use?
Operate Sast Toolchain is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Operate Sast Toolchain use?
About 1.3k tokens (SKILL.md is roughly 5.1k 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 955 tokens, read only when the agent opens those files.
What are the alternatives to Operate Sast Toolchain?
Skills that share tags, products or a category with Operate Sast Toolchain: Semgrep (vigolium/piolium, 140 stars), Semgrep Security Scan (trailofbits/skills, 7.5k stars), Sast Semgrep (AgentSecOps/SecOpsAgentKit, 220 stars) and Semgrep Rule Creator (trailofbits/skills, 7.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Operate Sast Toolchain?
cyberful (a GitHub organization) maintains it in cyberful/cyberful, which has 135 GitHub stars. The repository holds 85 skills in this directory. The repository was last updated on August 24, 2026.
Source: cyberful/cyberful on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.