capture0x/YeepForge / .claude/skills/yeepforge-sast
yeepforge-sast
VerifiedStatic application security testing (SAST) of a source-code directory using YeepForge's static analyzer. Use when the user provides a local code path and wants a vulnerability review - SQLi, XSS, RCE, SSRF, path traversal, XXE, SSTI, JWT, IDOR, missing auth, business logic, GraphQL. Requires the 'yeepforge' MCP server.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 2.0 KB |
SKILL.md
View on GitHub---
name: yeepforge-sast
description: "Static application security testing (SAST) of a source-code directory using YeepForge's static analyzer. Use when the user provides a local code path and wants a vulnerability review - SQLi, XSS, RCE, SSRF, path traversal, XXE, SSTI, JWT, IDOR, missing auth, business logic, GraphQL. Requires the 'yeepforge' MCP server."
---
# YeepForge - Source Code Security Analysis (SAST)
Drives YeepForge's `analyze_source_code` MCP tool (`mcp__yeepforge__analyze_source_code`)
to review a codebase for vulnerabilities before or alongside dynamic testing.
## When to use
- The user hands you a **local source path** and wants a security code review.
- You have dynamic findings and want to **confirm the root cause** in code.
- You want to find issues black-box testing can't reach (logic flaws, secrets,
unreachable-but-present sinks).
## How to run
1. Confirm the absolute path to the code directory.
2. Call `analyze_source_code` with:
- `code_path`: absolute path to the source directory.
- `skill`: `"all"` for a full pass, or a focused skill:
`architecture`, `sqli`, `xss`, `ssrf`, `rce`, `xxe`, `pathtraversal`,
`ssti`, `jwt`, `idor`, `missingauth`, `businesslogic`, `graphql`, `report`.
3. Start with `architecture` to map the app, then run targeted skills for the
sinks that matter (e.g. `sqli`, `rce`) rather than always running `all` on a
large codebase.
## Turning results into findings
- For each confirmed code-level vuln, record it with `report_finding`
(title, severity, OWASP category, the file/line evidence, remediation).
- Cross-check against dynamic results: a sink confirmed in code **and** reachable
at runtime is a high-confidence finding worth exploiting with
`exploit_vulnerability` (in scope only).
- Use `security-patterns` (vendored skill) regexes to sweep the code for leaked
API keys, tokens, and PII.
## Guardrails
- Only analyze code you are authorized to review.
- SAST flags **potential** sinks - validate reachability before reporting as
confirmed; note uncertain items as informational.
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |