cpra-sensitive-pi
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified. The skill consists of educational content and a local processing script with no external dependencies or dangerous capabilities.
- [SAFE]: Indirect prompt injection surface exists but is not exploitable within this skill. Data enters at scripts/process.py through function arguments without boundary markers or sanitization. However, the script contains no dangerous capabilities like subprocess calls, file writes, or network operations. Ingestion points: scripts/process.py (element_name and element_description parameters). Boundary markers: Absent. Capability inventory: None (script uses print statements only). Sanitization: Absent (only lowercases input for matching).
Audit Metadata