ladder-create
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- [Command Execution] (SAFE): The skill uses git commands for version control of generated documentation, which is appropriate for its stated purpose.
- [Indirect Prompt Injection] (SAFE): The skill ingests untrusted user input to generate phase specs, which is a theoretical surface for injection. Ingestion points: User-provided feature descriptions and Q&A responses. Boundary markers: No explicit delimiters are used when interpolating input. Capability inventory: Writing files and executing git commits. Sanitization: The risk is effectively mitigated by a mandatory USER REVIEW hard gate that requires the agent to present the full generated spec and receive explicit user approval before any persistent actions are taken.
Audit Metadata