adapt-workflow
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown content, checklists, and tables designed to guide the user through workflow adaptation.
- [SAFE]: No network operations, sensitive file access, or command execution patterns were detected. The skill mentions other internal tools like /agent-workflow and /evaluate but does not execute external code.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing user-supplied data via the target context argument but lacks any sensitive capabilities (such as file-system writes or network access) in the provided instructions, making it safe. 1. Ingestion points: SKILL.md (argument-hint); 2. Boundary markers: Absent; 3. Capability inventory: None; 4. Sanitization: Absent.
Audit Metadata