skill-management
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends using
pnpm dlx skills add oakoss/agent-skillsfor skill installation and discovery. This command interacts with the official 'skills' CLI and the author's repository, which is a standard procedure for skill management within this ecosystem.\n- [PROMPT_INJECTION]: The skill outlines a systematic procedure for auditing external content (other agent skills), which creates an indirect prompt injection surface as the agent is instructed to ingest and process files that could contain malicious instructions.\n - Ingestion points: The auditing process defined in
references/auditing-skills.md(Phase 1) requires reading all files in a target skill directory, includingSKILL.md, references, and scripts.\n - Boundary markers: The instructions do not specify any delimiters or safety markers for the content being analyzed during the audit phases.\n
- Capability inventory: The framework allows the agent to conduct systematic reviews and utilize the
pnpm validate:skillscommand on audited skills.\n - Sanitization: The skill relies on the 9-phase audit process itself as a validation mechanism rather than implementing automated sanitization of the input data.
Audit Metadata