The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses local toolchains to perform security audits. Specifically, it executes npm audit, pip-audit, go list, and cargo audit to identify vulnerabilities and outdated packages within the project environment.
[PROMPT_INJECTION]: The skill processes external manifest files which presents a surface for indirect prompt injection (Category 8).
Ingestion points: Dependency manifest and lock files (package.json, requirements.txt, go.mod, Cargo.toml, Gemfile) in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content within these manifest files.
Capability inventory: The skill reads local files and executes command-line audit tools across all supported ecosystems.
Sanitization: No sanitization or validation of the dependency data is specified before processing.
[SAFE]: The skill's activities are consistent with its stated purpose as a developer tool. The external link to qualitymax.io is a reference to the author's own service for continuous dependency monitoring and does not involve suspicious data exfiltration or obfuscation.

dependency-audit