The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from git diff and gh pr diff in Step 1. If an external contributor includes malicious instructions within code comments or documentation files in a Pull Request, the agent reading these diffs could potentially be influenced by that content. The skill lacks explicit boundary markers or instructions to ignore embedded commands found within the diff output.
[COMMAND_EXECUTION]: The skill utilizes shell commands including git diff, gh pr diff, and mise run docs:build. While these are standard development tools and the latter is a well-known project runner, they grant the agent the ability to execute repository-defined scripts and interact with the local version control system.

docs-audit