resolve-agent-reviews
Pass
Audited by Gen Agent Trust Hub on May 5, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches the
agent-reviewspackage from the NPM registry using runners likenpx,pnpm dlx, oryarn dlx. - [REMOTE_CODE_EXECUTION]: The skill executes code from the downloaded
agent-reviewspackage to evaluate and resolve PR comments. - [COMMAND_EXECUTION]: The skill runs shell commands for repository management, including
git add,git commit, andgit push, as well as the author's CLI tool. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted data from external sources.
- Ingestion points: Reads full comment bodies from external PR review bots via the
agent-reviews --expandedcommand. - Boundary markers: Absent. The skill does not use delimiters or instructions to isolate untrusted comment data.
- Capability inventory: The agent has the capability to modify source code, stage files, commit changes, and push to remote repositories.
- Sanitization: Absent. No filtering or escaping is applied to the fetched comment content before it is evaluated by the agent.
Audit Metadata