ai-code-review
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown text (
SKILL.md). It contains no executable scripts, shell commands, or configurations that interact with the host filesystem or network. - [NO_CODE]: No Python, Node.js, or other code files are present. The skill relies solely on prompting the agent to follow a specific review methodology.
- [PROMPT_INJECTION]: The instructions do not contain attempts to bypass safety filters, override system prompts, or extract internal instructions. The language used is purely task-oriented for code review.
- [METADATA_POISONING]: The YAML frontmatter accurately describes the skill's purpose and does not attempt to mislead the user or the agent regarding its capabilities.
Audit Metadata