npm-package-research
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the external npm registry, which presents a surface for indirect prompt injection if package descriptions or readmes contain malicious instructions.
- Ingestion points: Metadata, download stats, and maintainer information are ingested via the
strale_npm_package_infotool as described inSKILL.md. - Boundary markers: The skill does not define specific boundary markers or instructions to ignore instructions found within the fetched package data.
- Capability inventory: The skill utilizes
sandbase_call_toolto execute data retrieval commands. - Sanitization: No explicit sanitization or filtering of the external registry data is mentioned in the workflow instructions.
Audit Metadata