dependency-audit
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from package manifests and remote changelogs, creating a surface for potential indirect prompt injection.
- Ingestion points: Reads project manifest files (package.json, composer.json), lockfiles, and fetches remote changelogs or release notes via WebFetch.
- Boundary markers: The instructions do not include specific delimiters or warnings to ignore embedded instructions within the fetched package metadata or changelogs.
- Capability inventory: The skill has access to Bash (limited to composer/npm audit and outdated commands) and WebFetch for external data retrieval.
- Sanitization: No specific sanitization or filtering of the content retrieved from external URLs or local manifests is performed before processing.
Audit Metadata