specs-dev
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill defines a structured software development lifecycle (SDLC) using markdown-based planning and subagent orchestration.
- [PROMPT_INJECTION]: The skill exhibits an inherent surface for indirect prompt injection due to its core functionality of processing user requirements into code.
- Ingestion points: User-provided feature requests and requirements summary in Phase 1; session files (plan.md, tasks.md, handoff.md) in the session directory during Phases 2 and 3.
- Boundary markers: None explicitly defined in the subagent instructions to distinguish between instructions and potentially malicious data embedded in requirements.
- Capability inventory: The skill is designed to perform file system writes (writing implementation code and documentation), execute version control commands (Git commits), and run test suites.
- Sanitization: No explicit sanitization or validation of user-provided content is defined before it is processed by the implementation subagents.
Audit Metadata