pr-explainer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute several git commands to analyze the repository state, including
git status,git log,git diff, andgit show. These are standard development tools used for their intended purpose. - [INDIRECT_PROMPT_INJECTION]: The skill processes content from git diffs and commit messages, which are external, untrusted sources that could contain malicious instructions intended to manipulate the generated summary or HTML content.
- Ingestion points: Untrusted data enters the agent context through the output of
git diff,git log, andgit show(SKILL.md). - Boundary markers: There are no explicit instructions to use delimiters or ignore potential instructions embedded within the git output.
- Capability inventory: The skill is authorized to write local files to the
.pr-review/directory and suggest modifications to.git/info/exclude. - Sanitization: The instructions do not specify any validation, escaping, or sanitization of the content extracted from the git history before it is interpolated into the generated HTML report.
Audit Metadata