review-tests
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
git diffandgit logto inspect repository changes and history. These commands are fundamental to its stated purpose of reviewing code changes. - [EXTERNAL_DOWNLOADS]: It fetches content from an external issue tracker (following a defined workflow) and reads project documentation to understand the intended specifications of the changes being reviewed.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by processing untrusted data from git diffs and issue descriptions which are then passed to a sub-agent for analysis.
- Ingestion points: Data is pulled from
git diff,git log, and issue tracker summaries as described inSKILL.md. - Boundary markers: The instructions for the sub-agent lack explicit delimiters or 'ignore' instructions for the provided input data.
- Capability inventory: The skill is limited to read-only operations, git command execution, and spawning analysis sub-agents.
- Sanitization: No specific sanitization or filtering of the input data is described.
Audit Metadata