github-code-review
Fail
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: HIGHDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The
webhook-handler.jsexample provided in the documentation usesexecSyncto execute shell commands constructed using unvalidated input from GitHub webhook payloads (event.comment.body). This implementation introduces a command injection vulnerability, potentially allowing any user who can comment on a pull request to execute arbitrary code on the runner. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from GitHub, including PR titles, bodies, and diffs, which are then used to influence the behavior of the AI agents and subsequent repository actions.
- Ingestion points: PR data is fetched via
gh pr viewandgh pr diffcommands throughoutSKILL.md. - Boundary markers: None; external PR content is passed directly to the swarm analysis tools as string arguments.
- Capability inventory: The skill has significant capabilities including
gh pr review(commenting, approving, requesting changes),gh pr edit(labeling), andgh pr merge(merging code). - Sanitization: The skill lacks explicit sanitization or escaping mechanisms for the PR content it processes.
- [COMMAND_EXECUTION]: The skill heavily relies on executing shell commands via the GitHub CLI (
gh) andnpxto perform repository management tasks, including automated code merging and labeling. - [REMOTE_CODE_EXECUTION]: The skill frequently uses
npxto download and execute theruv-swarmpackage. While this tool is associated with the skill's vendor, the use ofnpxinvolves fetching and running remote code during execution.
Recommendations
- AI detected serious security threats
Audit Metadata