validate-before-share
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to fetch and interpret external content to ensure it matches specific expectations like page titles or JSON shapes.
- Ingestion points: The agent performs HTTP GET requests on external production URLs and local development endpoints (SKILL.md).
- Boundary markers: The skill does not define delimiters or specific instructions to ensure the agent ignores natural language instructions that might be contained within the fetched content.
- Capability inventory: The agent uses its network tools to retrieve content and its reasoning capabilities to validate the response body.
- Sanitization: No mechanisms for sanitizing or filtering instructions from the retrieved content are mentioned or required.
Audit Metadata