implement-spec
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data (specifications and tickets) to drive a complex workflow involving multiple subagents and code implementation. This introduces a surface for indirect prompt injection where malicious instructions embedded in a spec or ticket could potentially influence the behavior of the agent or its subagents.
- Ingestion points: The skill reads specifications and ticket task graphs from an external issue tracker or user-provided files (SKILL.md).
- Boundary markers: No specific delimiters or safety instructions are defined to separate the external task data from the agent's core instructions.
- Capability inventory: The skill possesses significant capabilities including git branch/merge management, file system operations (saving notes, creating worktrees), and the invocation of other tools like 'tdd' and 'code-review' (SKILL.md).
- Sanitization: The instructions do not specify any validation or sanitization steps for the data retrieved from the spec or tickets before it is used to generate tasks for implementer subagents.
Audit Metadata