skills/clawlink-hq/skills/prisma/Gen Agent Trust Hub

prisma

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the @useclawlink/cli tool via npx. This is the intended primary purpose of the skill to facilitate integration between the agent and Prisma.
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and run the @useclawlink/cli package from the official NPM registry. This is a standard practice for CLI-based integrations.
  • [CREDENTIALS_UNSAFE]: The documentation explicitly mentions that credentials are stored at ~/.clawlink/credentials.json. It correctly advises against hardcoding API keys and instead uses a browser-based login flow, which is a safer practice for secret management.
  • [DATA_EXFILTRATION]: While the skill connects to an external service (ClawLink), it does so to perform its stated function (integrating Prisma). There are no patterns suggesting unauthorized exfiltration of sensitive files or system data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 05:45 PM