osv-scanner
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by scanning lockfiles and source trees. Maliciously crafted content within these files could attempt to manipulate the agent's analysis or reporting process. * Ingestion points: Scans project lockfiles and the resolved source tree (SKILL.md). * Boundary markers: Absent; the instructions do not provide delimiters or warnings to treat the scanned file content as untrusted. * Capability inventory: The agent reads local file content and passes findings to a verification endpoint (
/verify-security-finding). * Sanitization: Not specified; the agent evaluates vulnerable-feature use based on the raw content of the source tree.
Audit Metadata