privacy-data-protection
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely composed of instructional markdown and a schema template. It lacks any executable scripts, binaries, or configuration files that could facilitate malicious activity.
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to scan and map data schemas for PII. While processing external schema data is an inherent ingestion point for untrusted content, the skill does not introduce dangerous tools, file-writing capabilities, or network operations that could be exploited via indirect injection.
- [DATA_EXFILTRATION]: The skill includes explicit security guardrails instructing the agent to never output plaintext records from scanned databases. This practice focuses the agent on structural analysis rather than data retrieval, reducing the risk of accidental PII exposure.
Audit Metadata