interface-review
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes common CLI tools including
git,gh, andgrepto inspect repository states and diff content. These commands are limited to local repository analysis and do not request administrative permissions. - [EXTERNAL_DOWNLOADS]: The skill retrieves pull request metadata and source code from GitHub using
git fetchand the GitHub CLI. These downloads are directed to the project's official origin and are necessary for its code review functionality. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted data from source code repositories and pull request descriptions. * Ingestion points: The skill ingests data from the output of
git diff,git show, andgh pr view. * Boundary markers: There are no explicit instructions to use delimiters or warnings to ignore instructions embedded within the ingested code. * Capability inventory: The skill can execute shell commands viagit,gh, andgrep, but it is restricted from performing file-write operations or checkouts that modify the working tree. * Sanitization: The instructions do not specify any sanitization or filtering of the ingested diff data or metadata before analysis.
Audit Metadata