netra-pii-and-input-guardrails
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill defines a regex pattern 'INJECTION_RE' used to identify common injection attempts such as 'ignore previous instructions' or 'reveal system prompt'. This is a defensive security measure rather than a malicious attempt to override instructions.
- [EXTERNAL_DOWNLOADS]: The skill references the 'netra' and 'netra-sdk' libraries for Python and TypeScript. It also includes links to official documentation at 'getnetra.ai'. These resources are consistent with the skill's stated purpose of implementing security monitoring and filtering.
Audit Metadata