The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes a Python script scripts/analyze_git_commits.py that executes local git commands (such as git log, git diff, and git rev-parse) using subprocess.run. This is used to gather branch information and commit history for the PR description generation process.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git commit messages and existing pull request descriptions. Malicious content within these sources could attempt to influence the agent's output by including hidden instructions.
Ingestion points: Commit subjects and bodies extracted by scripts/analyze_git_commits.py; existing PR descriptions provided by the user when updating or reviewing PRs.
Boundary markers: Absent. The skill does not use specific delimiters or instructions for the agent to ignore potentially malicious embedded commands when processing the analyzed git data.
Capability inventory: The skill is limited to reading git repository data and generating text descriptions; it does not possess capabilities for network access or file system modifications.
Sanitization: No sanitization, escaping, or filtering is performed on the commit messages or PR text before they are interpolated into the prompt context.

pr-description-writer