ask-pi
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and documents the legitimate use of a command-line utility for automation.
- [COMMAND_EXECUTION]: The skill describes how to execute the 'pi' tool with various flags. This is the intended purpose of the skill and does not involve unauthorized commands.
- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes external data. 1. Ingestion points: Data is read from stdin and local files like README.md (SKILL.md). 2. Boundary markers: No explicit delimiters are used in the documentation examples. 3. Capability inventory: The skill uses the 'pi' CLI. 4. Sanitization: No input validation or sanitization is described. This is a standard risk factor for data processing tools.
Audit Metadata