The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the official GitHub CLI (gh) and standard git commands (git log, git diff, git status) to gather branch information and manage pull requests.
[DATA_EXPOSURE_AND_EXFILTRATION]: While the skill reads git history and diffs, it includes explicit instructions in references/body-template.md to avoid pasting secrets, tokens, or full lockfile dumps into the PR description. Network operations are restricted to the official GitHub API via the gh tool.
[PRIVILEGE_ESCALATION]: The skill operates within the user's existing permissions. It explicitly handles cases where a user might not have write access to a repository, instructing the agent to report permission errors plainly or use a fork.
[REMOTE_CODE_EXECUTION]: There are no patterns of downloading or executing external scripts. All logic is contained within the skill's instructions and standard local tooling.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from git log and git diff to generate PR bodies. However, it uses structured templates and human-in-the-loop triggers (requesting confirmation before pushing or overwriting), mitigating the risk of instructions in commits being executed by the agent.

pull-request-authoring