skill-audit
Pass
Audited by Gen Agent Trust Hub on Aug 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data from multiple files across the repository, creating a surface for indirect prompt injection where malicious content in a file being audited could attempt to override the agent's behavior.
- Ingestion points: The
scripts/audit_skills.pyscript reads and parses content fromSKILL.mdfiles,evals/evals.json,.claude-plugin/plugin.json,website/src/data/skills.ts, and project documentation (e.g.,README.md,USAGE.md). - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when the agent is instructed to process or report on the content of these files.
- Capability inventory: The agent is instructed to perform file modifications ("Repair, only when asked") and execute shell commands (running the audit script and
pytest) based on the findings from the audited files. - Sanitization: There is no evidence of sanitization or filtering to prevent instructions within the audited files from being interpreted as commands by the agent.
Audit Metadata