claim-check
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script (scripts/claim_check.py) to process files. The script is included in the skill package and uses only standard Python libraries without network access.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided text files and presents snippets to the agent, creating a surface where malicious instructions in the scanned files could potentially influence agent behavior.\n
- Ingestion points: scripts/claim_check.py reads content from files specified by the user.\n
- Boundary markers: Findings are formatted as structured reports, though specific delimitation for raw text snippets is minimal.\n
- Capability inventory: The script performs read-only operations and has no network or write capabilities.\n
- Sanitization: Text is truncated for display but not otherwise sanitized against prompt injection patterns.
Audit Metadata