ha-pr-reviewer
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources (GitHub pull request descriptions and code diffs) via the
gh pr viewandgh pr diffcommands. - Ingestion points: Pull request details and code changes are pulled into the agent's context in
SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands in the PR content are present.
- Capability inventory: The skill is restricted to read-only operations via the GitHub CLI. It delegates the review to
ha-reviewandha-pr-comment-auditskills and contains a explicit directive to only output feedback to the console and not act on GitHub. - Sanitization: The skill does not perform sanitization or filtering of the ingested PR data.
Audit Metadata