site-history
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external websites and local project documentation, creating an attack surface where data from these sources could influence agent behavior.
- Ingestion points: Reads from the local PROJECT.md file and fetches content from external websites via WebFetch.
- Boundary markers: The skill lacks explicit instructions or delimiters to isolate ingested data from agent instructions.
- Capability inventory: The agent has access to WebSearch, WebFetch, Write, Edit, Read, and Bash tools.
- Sanitization: No explicit logic or instructions are provided to sanitize or validate the retrieved information.
- [EXTERNAL_DOWNLOADS]: The skill fetches architectural and planning data from trusted domains, including nyc.gov, nps.gov, and loc.gov.
Audit Metadata