sdd-yolo
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes external content from docs/project.md and user input to generate code. This represents an indirect prompt injection surface.
- Ingestion points: docs/project.md and feature_description argument.
- Boundary markers: No explicit delimiters are used to wrap external content.
- Capability inventory: File system access and shell command execution for testing.
- Sanitization: The skill does not specify input validation.
- Mitigation: This risk is mitigated by a mandatory human confirmation gate and a final security review phase.
- [COMMAND_EXECUTION]: The skill runs local shell commands for development tasks.
- Evidence: Executes test commands in Phase 3 and git diff in Phase 4.
- Context: This is standard functionality for the skill's purpose.
Audit Metadata