brief
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to search for keywords and analyze the top search results to identify intent and content gaps. Content found on external websites is untrusted and could contain hidden instructions designed to influence the agent's behavior during the content briefing process.
- Ingestion points: Results from web searches and competitive SERP reviews (Step 1).
- Boundary markers: The skill provides a structured output format but does not explicitly instruct the agent to disregard instructions potentially embedded within the analyzed web content.
- Capability inventory: The skill utilizes web search capabilities; it does not demonstrate risky file system or network writing capabilities.
- Sanitization: There is no evidence of sanitization or filtering of the retrieved search data before it is processed into the brief.
Audit Metadata