data-expert
Pass
Audited by Gen Agent Trust Hub on Apr 23, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for secure and efficient data processing, including requirements for input validation and redaction of sensitive information.
- [SAFE]: The skill contains an indirect prompt injection surface as it reviews untrusted user-provided content. This is mitigated by 'Iron Laws' requiring mandatory validation and sanitization. Ingestion points: User-provided code and data (SKILL.md). Boundary markers: Absent. Capability inventory: Bash, Read, Write, Edit, Grep, Glob (SKILL.md). Sanitization: Mandated by internal rules (SKILL.md).
Audit Metadata