workflow-feature-with-integration-test

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill passes the user's prompt as context to a workflow orchestrator. This creates a surface for indirect prompt injection where malicious instructions embedded in the user input could attempt to subvert the logic of subsequent automated steps.
  • Ingestion points: User prompt context passed to /workflow-start in SKILL.md.
  • Boundary markers: No explicit delimiters or "ignore previous instructions" safety warnings are defined for the context interpolation.
  • Capability inventory: The workflow orchestrates high-privilege operations including code generation (/cook), test execution (/test), and system review (/sre-review).
  • Sanitization: No sanitization or validation of the user input is performed before it is integrated into the workflow context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 03:49 AM