From fabrik
Performs security reviews by starting from a random file, tracing one deep path through imports and data flows, and reporting the single most significant issue or none found.
How this skill is triggered — by the user, by Claude, or both
Slash command
/fabrik:security-reviewThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Pick a random starting point by running the bundled script:
Pick a random starting point by running the bundled script:
bash scripts/random-file.sh
The scripts/ directory is part of this skill, not the project repository.
The random entry point is intentional: it forces exploration of parts of the codebase that might otherwise be overlooked. The idea is to run this skill multiple times over the life of a project, each time pulling one thread from a different starting point.
Read the file the script returned. From there, follow one promising path -- a single thread of connections (imports, callers, callees, data flow) that looks like it could harbor a security issue. Go deep on that one path rather than trying to survey everything.
Report exactly one finding -- the single most significant security issue you discovered along the path. Not two, not a list, just one. If nothing concerning was found, say so -- that's a valid outcome. Resist the temptation to pad the report with minor observations or informational notes.
npx claudepluginhub maragudk/fabrik --plugin fabrikScans codebases for security vulnerabilities using data flow analysis. Covers injection, auth, secrets, crypto, and dependencies across multiple languages (JS, TS, Python, Java, Go, PHP, Ruby, Rust).
Conducts security-focused code reviews to detect SQL injection, XSS, authentication flaws, and insecure dependencies. Activated by phrases like 'security scan' or 'audit'.
Reviews code for security vulnerabilities including injection, XSS, authentication, and cryptography issues. Provides systematic review with confidence-based reporting.