package-scout
Pass
Audited by Gen Agent Trust Hub on Oct 31, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to search for and ingest package data from the web, which could potentially contain malicious instructions.
- Ingestion points: External package information and search results from registries like npmjs.com and GitHub (SKILL.md).
- Boundary markers: The skill does not define specific delimiters for the external content it processes.
- Capability inventory: The agent can execute package installation commands (npm, pnpm, yarn, bun) after completing the research phase (SKILL.md).
- Sanitization: The workflow requires the agent to verify package health using social signals (downloads, stars) and vulnerability scanners (Snyk, Socket.dev).
Audit Metadata