supabase

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill exposes actions that can read stored credentials and explicitly includes a "supabase_list_secrets" action and a stored credential file (~/.clawlink/credentials.json), which means the agent may retrieve and output secret values verbatim, creating an exfiltration risk.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). This skill grants an AI agent programmatic access to Supabase including listing secrets/backups, running arbitrary SQL, and creating/deploying edge functions—capabilities that enable data exfiltration, credential theft, and remote code execution if misused or if the agent/ClawLink credential is compromised.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill instructs the agent to run "npx @useclawlink/cli" at runtime, which fetches and executes remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli) and relies on that external CLI (and ClawLink endpoints like https://claw-link.dev) as a required runtime dependency that can control agent behavior.