enterprise-context
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions aimed at improving the reliability of agent responses through systematic searching and source attribution.\n- [PROMPT_INJECTION]: The skill describes an indirect prompt injection attack surface.\n
- Ingestion points: The skill ingests data from
gemini_enterprise_searchandgemini_enterprise_get_document(SKILL.md).\n - Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions within the search results.\n
- Capability inventory: The agent can retrieve and read full documents based on search queries (SKILL.md).\n
- Sanitization: Absent; the skill does not require validation or filtering of document content before processing.
Audit Metadata