tk-code-review
Pass
Audited by Gen Agent Trust Hub on Jul 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill employs standard
gitcommand-line utilities (such asrev-parse,diff, andlog) to inspect repository history and retrieve code changes for analysis. These operations are read-only and restricted to the repository scope. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from git diffs and repository documentation which could contain malicious instructions designed to manipulate the agent's output.
- Ingestion points: Git diff output and repository files like
.tigerkit/spec.mdorCONTRIBUTING.mdas described in the Workflow sections ofSKILL.md. - Boundary markers: Absent. The instructions do not define clear delimiters or use "ignore embedded instructions" warnings for the ingested diff content.
- Capability inventory: Shell execution of git commands and system file-read access within the repository path.
- Sanitization: No sanitization or filtering of the external code content is performed before it is processed by the agent.
Audit Metadata