matthew-a-carr/implement-spec
Implement an approved feature specification. Triggered by a routine when a spec PR is merged with the `ai:implement` label (per ADR 057), or by a human asking "implement SPEC-NNN" interactively. Follows the spec's implementation order using TDD, logs deviations, runs the full verification suite, opens an implementation PR with label `ai:done`, and closes out the spec with post-implementation notes and tech debt capture.
78
90%
Does it follow best practices?
Impact
100%
2.56xAverage score across 1 eval scenario
Advisory
Suggest reviewing before use
Security
1 medium severity finding. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
Third-party content exposure detected (high risk: 0.85). The skill reads the merged SPEC PR’s body/changed files and then reads the spec file end-to-end via `mcp__github__pull_request_read` (outsider-authored PR content), which becomes LLM-readable prose in the implementation context.
- Audited
- Security analysis