The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local repository state to generate pull request content.
Ingestion points: Reads output from git status, git log, and git diff in Step 1 and Step 2 to inform the PR description.
Boundary markers: The instructions do not define specific delimiters or instructions to ignore malicious patterns embedded within commit messages or code diffs.
Capability inventory: The skill uses git and the GitHub CLI (gh) to perform repository operations and create pull requests.
Sanitization: There is no explicit sanitization of the data retrieved from git before it is used to generate the PR body.
[EXTERNAL_DOWNLOADS]: The skill references documentation and guidelines from Sentry's official developer portal (develop.sentry.dev). These are informative references to a well-known service used for providing context on coding standards.
[COMMAND_EXECUTION]: The skill relies on executing git and gh shell commands to manage branches and create pull requests. These are standard operations for the skill's stated purpose.

create-pr