fact-check
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external, untrusted text which serves as a significant attack surface for prompt injection.
- Ingestion points: The skill accepts draft text directly or from files to extract and verify factual claims (SKILL.md).
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore commands potentially embedded within the ingested drafts.
- Capability inventory: The agent is directed to use external search tools and visit user-supplied URLs to verify claims (SKILL.md).
- Sanitization: There are no documented mechanisms for sanitizing or filtering the untrusted data before processing.
Audit Metadata