pie-power-systems
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data through InfrastructureRequest objects to perform electrical design calculations and safety validations. This creates a surface for indirect prompt injection where malicious instructions could be embedded in the processed data.
- Ingestion points: Data entered via InfrastructureRequest fields and voltageClass constraints specified in SKILL.md.
- Boundary markers: Absent. There are no explicit delimiters or instructions defined to isolate external data from the agent's logic.
- Capability inventory: The skill has access to Read, Grep, Glob, and Bash tools.
- Sanitization: No sanitization, validation, or escaping of external infrastructure data is implemented.
Audit Metadata