meow-review

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes several subcommands of the mfl (MeowFlow) CLI tool, including status, thread status, and handoff. It also invokes pnpm to run repository-specific scripts for validation. These commands are integral to the skill's function as a code reviewer.
  • [EXTERNAL_DOWNLOADS]: The instruction to run mfl agent update-self indicates a self-updating mechanism for the agent's CLI component. As this is a vendor-provided tool (MeowFlow) for the developer's workflow, this is a standard administrative operation.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources such as git diffs and thread statuses via mfl thread status. While processing untrusted data (like code diffs) is an attack surface, it is the primary intended function of a code review tool. No high-risk capabilities are exposed to this untrusted data without user-defined context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 04:00 PM
Security Audit — agent-trust-hub — meow-review