The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to interact with the local repository, specifically git diff, git log, and git rev-parse to retrieve change data and validate references.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository (diffs and documentation) and incorporates it into prompts for parallel sub-agents without explicit sanitization or boundary markers.
Ingestion points: Output from git diff and git log (Step 1), fetched contents of specifications (Step 2), and repository standards files like CODING_STANDARDS.md (Step 3) are all used to populate sub-agent prompts.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when interpolating the diff and spec content into sub-agent prompts in Step 4.
Capability inventory: The skill has the ability to execute shell commands (git), read arbitrary local files, and spawn sub-agents with dynamically generated prompts.
Sanitization: There is no evidence of escaping, validation, or filtering of the external code or documentation content before it is processed by the sub-agents.

code-review