workflow-start
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of markdown instructions that guide the agent through a specific workflow process. No malicious code, obfuscation, or unauthorized commands were detected.
- [PROMPT_INJECTION]: The skill uses strong instructional language (e.g., '[MANDATORY]', 'ALWAYS') to ensure task compliance. These instructions do not attempt to bypass safety guidelines or extract system prompts; they are focused on operational consistency.
- [EXTERNAL_DOWNLOADS]: The skill references local hooks (
workflow-step-tracker.cjs,workflow-router.cjs) and an 'injected catalog'. These are described as internal components of the agent's environment and do not involve fetching data or code from untrusted external URLs.
Audit Metadata