The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by running git diff --staged as instructed in SKILL.md. It does not provide boundary markers or instructions to the agent to disregard commands that might be embedded within the source code being analyzed. While the skill's instructions are limited to generating text, the ingestion of raw code changes creates an attack surface where malicious comments or strings in the staged changes could attempt to influence the agent's output.

commit-helper