Skills
Navigate
skills/edheltzel/do-skills/do-red-team/Gen Agent Trust Hub

do-red-team

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted user content which is then interpolated into prompts for parallel adversarial personas. Ingestion points: User arguments are processed in Workflows/ParallelAnalysis.md and problem descriptions in Workflows/AdversarialValidation.md. Boundary markers: Markdown headers and <instructions> tags are used to separate instructions from user data. Capability inventory: The skill utilizes the Task tool for parallel execution and integrates with reasoning-focused skills like do-first-principles. Sanitization: No specific sanitization or filtering of user input is implemented within the workflow logic.
  • [SAFE]: No other security concerns were identified, including credential harvesting, remote code execution, or persistence mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 08:32 PM