skills/openclaw/clawhub/convex-verify/Gen Agent Trust Hub

convex-verify

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run tests using npx vitest run, which is a standard operation for a testing utility.
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing convex-test, vitest, and @edge-runtime/vm as development dependencies. These are standard, well-known packages for the described testing environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined code and feature specifications to generate and run tests. While this involves ingesting untrusted data, the skill includes instructions to ask the user for clarification if the intent is unstated and focuses on validating security through negative assertions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:14 PM