implement-spec
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data from a specification and an issue tracker to drive implementation tasks.
- Ingestion points: The agent reads specifications and tickets from an issue tracker to build a task graph and guide subagents.
- Boundary markers: The instructions lack explicit delimiters or warnings to prevent the subagents from interpreting ticket content as system-level instructions.
- Capability inventory: The skill possesses significant capabilities, including managing Git branches, writing code across multiple worktrees, and executing tools for testing (tdd) and review (code-review).
- Sanitization: There is no evidence of sanitizing or validating the content of the tickets before it is provided to the exploration and implementer subagents.
Audit Metadata