check
Pass
Audited by Gen Agent Trust Hub on Mar 22, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by executing scripts defined in the local project's environment.
- Ingestion points: The skill reads project lock files and relies on local script definitions for execution.
- Boundary markers: No delimiters are present to isolate the shell execution.
- Capability inventory: Access to the Bash tool for running local scripts.
- Sanitization: No validation or filtering of the script content is performed, which is expected behavior for this tool's primary purpose.
- [SAFE]: The skill operates as intended for a development tool and does not exhibit malicious intent or exfiltration behavior.
Audit Metadata