audit-recon
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions.
- Ingestion points: Reads project files (Step 1) and fetches data from the web (WebFetch/WebSearch).
- Boundary markers: None identified. Instructions do not specify delimiters for external content.
- Capability inventory: Includes high-privilege tools such as 'Bash' and 'Write' which could be abused if an injected instruction is followed.
- Sanitization: No explicit sanitization or validation of the ingested legal artifacts or web content is defined in the instructions.
Audit Metadata