vector-db-search
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection by accepting natural language queries that are passed to a search script.\n- Ingestion points: The natural language query parameter used in the
python ./scripts/query.pycommand withinSKILL.md.\n- Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the command examples.\n- Capability inventory: The skill is configured to useBashandReadtools to execute scripts and read repository content.\n- Sanitization: There is no evidence of sanitization or validation of the search query in the documentation provided.
Audit Metadata