claim-extraction
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input text chunks to extract specific factual claims. This creates an attack surface where malicious content embedded in the source text could attempt to override the extraction instructions or influence downstream processing steps in the agent's workflow.
Audit Metadata