implement-spec
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to ingest and process external specifications and task tickets to drive a multi-agent implementation workflow. This creates a surface for indirect prompt injection where malicious instructions embedded in a specification could attempt to influence the agent or its subagents.
- Ingestion points: External specifications and task graph tickets read in SKILL.md.
- Boundary markers: The instructions do not define clear delimiters or instructions for the agent to distinguish between its own logic and potentially adversarial content within the specs.
- Capability inventory: The workflow utilizes subagents with capabilities for branch management, worktree creation, merging code, and invoking code review tools.
- Sanitization: No validation or sanitization of the specification data is performed prior to it being used to guide the implementation process.
Audit Metadata