fact-check
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from web and academic databases (Google, Semantic Scholar, ArXiv) to verify claims. This creates a vulnerability surface where malicious instructions embedded in external sources could attempt to influence the agent's reasoning, assessment, or subsequent tool use.
Audit Metadata