pii-and-compliance
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of instructional text and code examples designed to improve security by identifying PII and credential leaks. It does not perform any network operations, file system modifications, or command executions.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data (code diffs). It includes a structured 'Finding-shape template' which helps the agent maintain clear boundaries between the analyzed data and its instructions. The risk is considered minimal as the skill's capabilities are limited to generating descriptive text feedback for the user.
Audit Metadata