open-code-review-delegate
Pass
Audited by Gen Agent Trust Hub on Aug 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
@alibaba-group/open-code-reviewpackage from npm, which is the official CLI tool provided by the vendor. - [COMMAND_EXECUTION]: The skill uses the
ocrCLI to preview changes and retrieve review rules. It also utilizesgitandcatto fetch code diffs and file contents for the review process. - [PROMPT_INJECTION]: The skill exposes the agent to indirect prompt injection risks as it ingests and processes untrusted code from external repositories.
- Ingestion points: Code content is read using
git diff,git show, andcatfrom the local workspace or repository history. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified in the prompt logic.
- Capability inventory: The skill possesses the capability to execute shell commands and install packages.
- Sanitization: No sanitization or filtering of the ingested code content is performed before it is presented to the agent for review.
Audit Metadata