workflow-enforcer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Prompt Injection (LOW): The skill employs strong directive language such as 'No exceptions, no rationalizations, no shortcuts' and 'applies to EVERY session' to override the AI's default task-handling logic and enforce compliance with its specific protocol.
- Indirect Prompt Injection (LOW): The skill creates a vulnerability surface by delegating tasks to specialized agents based on unsanitized user input. Evidence: 1. Ingestion points: User requests are categorized into task types within SKILL.md. 2. Boundary markers: Absent for user input interpolation. 3. Capability inventory: Orchestrates calls to specialized agents including security-auditor and deployment-engineer. 4. Sanitization: No sanitization or validation of the user request is performed before delegation.
Audit Metadata