The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute git commands including git status, git log, git diff, and git show to collect information about pull requests and code changes.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from pull request diffs and commit messages.
Ingestion points: Content from git diff, git log, and git show outputs are processed to generate the HTML report.
Boundary markers: The instructions do not specify any markers or delimiters to isolate untrusted code content from the analysis logic.
Capability inventory: The skill has the capability to execute shell commands (git) and write files to the local .pr-review/ directory.
Sanitization: There is no mention of sanitizing or escaping the content retrieved from the git repository before it is included in the generated HTML.

pr-explainer