The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill inherently interacts with untrusted data by reading the repository state, git diffs, and pull request metadata, which could contain malicious instructions from external contributors. However, this is a standard and necessary function for the skill's stated purpose as a developer tool.
Ingestion points: The skill uses git status, git rev-parse, and a change-scope utility to read the state of the repository as described in SKILL.md.
Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore embedded instructions within the git output or code files.
Capability inventory: The skill is authorized to execute a variety of shell commands, including pnpm run for testing and building, as well as git push and gh CLI operations for managing remote branches and PRs.
Sanitization: The instructions do not specify any validation or sanitization of the repository metadata or file contents before they are processed by the agent.

dsh-pre-push-checks