factchk
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes assertions and artifacts that may contain content from untrusted external sources or user input. This creates an attack surface where instructions hidden in the processed text could influence the agent's verification process or output.
- Ingestion points: Scans artifacts and text provided for fact-checking in the 'Workflow' section (SKILL.md).
- Boundary markers: There are no explicit delimiters or instructions to ignore potential commands embedded in the data being verified.
- Capability inventory: The skill uses external tools for 'web search' and has the capability to 'Fix' or modify the artifact being analyzed (SKILL.md).
- Sanitization: The instructions do not specify any sanitization or validation of the input content before processing.
Audit Metadata