alan-review-pr
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external GitHub pull requests, creating a risk that malicious instructions embedded in that data could influence the agent's behavior.
- Ingestion points: Pull request metadata (title, description), unified diffs, and pull request comments are fetched via
mcp__alan__github_get_pull_request,mcp__alan__github_get_pr_diff, andmcp__alan__github_list_pr_commentsinSKILL.md. - Boundary markers: The workflow does not define any delimiters or specific instructions to treat content from the pull request as untrusted data rather than commands.
- Capability inventory: The skill uses tools that can perform sensitive operations on the repository, including
mcp__alan__github_create_pr_review,mcp__alan__github_merge_pull_request,mcp__alan__github_close_issue, andmcp__alan__github_add_comment. - Sanitization: There are no instructions to sanitize or validate the content retrieved from the GitHub API before analysis.
Audit Metadata