requesting-code-review
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external data (git diffs) which could contain adversarial instructions intended to influence the subagent's review results. \n
- Ingestion points: The
code-reviewer.mdtemplate is populated with output fromgit diffcommands. \n - Boundary markers: Absent; the diff content is not delimited, and there are no instructions to the subagent to ignore embedded commands. \n
- Capability inventory: The skill uses
git rev-parseandgit diffvia shell commands. \n - Sanitization: No input sanitization or output filtering is implemented for the code content being reviewed. \n- [COMMAND_EXECUTION]: The skill uses placeholders
{BASE_SHA}and{HEAD_SHA}directly inside shell command blocks incode-reviewer.md. This represents a command injection surface if the commit references provided to the template are not strictly validated as legitimate git SHAs.
Audit Metadata