workflow-verification

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or behaviors detected. The skill operates as a workflow orchestrator for standard software development tasks using internal commands.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by passing user input as context to a multi-step execution chain.\n
  • Ingestion points: The user prompt is ingested as context in the /workflow-start command within SKILL.md.\n
  • Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted user input from instructions.\n
  • Capability inventory: The workflow invokes tools (/scout, /test, /fix, /code-review) which imply capabilities for file system access, testing, and code modification.\n
  • Sanitization: No sanitization or validation of the user's input is specified in the skill configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:24 AM