best-practices
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources, creating a vulnerability where malicious instructions in web content could influence the agent.
- Ingestion points: External content is retrieved using
WebSearch,WebFetch, andfind-docs(SKILL.md). - Boundary markers: No delimiters or "ignore instructions" warnings are defined for the fetched data.
- Capability inventory: The skill has access to
WebSearch,WebFetch, andBash(SKILL.md). - Sanitization: No sanitization or validation is performed on external data before synthesis.
Audit Metadata