plan-review
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses git commands (
git log,git diff,git stash) to audit the project state. These are standard read-only operations used to provide context for the review. - [DATA_EXFILTRATION]: Output is directed to a hardcoded Feishu folder ID (
LlLAfpr9Al4bFsdYuXScz2mHnY7). This is documented as the primary intended workflow for the skill and does not constitute unauthorized exfiltration. - [PROMPT_INJECTION]: The skill uses instructional framing like 'Nuclear Scope Challenge' and 'CEO/Founder mode' to guide the AI's persona. These instructions are transparent, functional for the review process, and do not attempt to bypass platform safety constraints or extract system prompts.
Audit Metadata