The Agent Skills Directory

[SAFE]: The skill consists of instructional content defining software engineering standards for TDD reviews. It does not contain executable code, external dependencies, or network operations.
[DATA_EXPOSURE]: The instructions describe the analysis of project metadata, specifically execution-log.json and git diff output, which is standard behavior for a code review or linting skill.
[PROMPT_INJECTION]: No attempts to override system prompts or bypass safety guardrails were detected. The use of strong language like 'BLOCKER' and 'REJECTED' is contextual to the skill's purpose as an enforcement tool for TDD discipline.
[INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface by instructing the agent to ingest and act upon external data.
Ingestion points: The skill references processing execution-log.json and git diff output.
Boundary markers: There are no explicit instructions to ignore or delimit instructions that might be embedded in the logs or code diffs.
Capability inventory: The agent is instructed to perform file reads and git operations to identify 'Detection Signals'.
Sanitization: No sanitization or validation of the ingested data is specified.

nw-tdd-review-enforcement