afk-interactive-code-review
Pass
Audited by Gen Agent Trust Hub on Jun 19, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The workflow utilizes git diff and git grep to inspect code changes and identify impacted files. These commands are fundamental to the skill's purpose and are used in a read-only manner within the repository environment.
- [PROMPT_INJECTION]: The skill processes untrusted code from Git branches which could potentially contain malicious instructions or specially crafted tokens designed to influence the agent's behavior during the review process. Ingestion points: Code content is read via git diff and git grep commands as described in SKILL.md. Boundary markers: Absent; code contents are processed directly without explicit isolation from instructions. Capability inventory: The skill uses shell-based tool execution (git) for repository analysis. Sanitization: No specific sanitization or validation of extracted code tokens is mentioned before they are used in subsequent search commands.
Audit Metadata