phantombuster

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). At runtime, the skill’s phantombuster_get_* / phantombuster_get_script* actions fetch PhantomBuster content (e.g., agent/script details and outputs) from PhantomBuster’s service, which is outsider-authored free text that the agent ingests into its LLM context.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill requires running npx @useclawlink/cli which fetches and executes the remote @useclawlink/cli package from npm (https://www.npmjs.com/package/@useclawlink/cli) and interacts with ClawLink (https://claw-link.dev), so remote code is downloaded and executed at runtime and is required for the skill to function.