secure-dependencies
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection (Category 8) by design.
- Ingestion points: The tool processes external data including repository manifests, lockfiles, and CI configuration via the $ARGUMENTS parameter.
- Boundary markers: No delimiters or protective instructions are used to distinguish ingested data from the skill's own instructions.
- Capability inventory: The skill's instructions require the agent to inspect files and execute validation/install commands.
- Sanitization: There is no logic provided to sanitize or validate the content of the files being processed.
Audit Metadata