exist

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow invokes ClawLink/Exist via shell commands (e.g., actions/describe/run exist), which can fetch and ingest outsider-authored free text from the connected third-party app (Exist) into the agent’s LLM context as action descriptions/results.

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

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs the agent to run npx @useclawlink/cli (https://www.npmjs.com/package/@useclawlink/cli), which causes npx to fetch and execute remote code from the npm registry at runtime and is a required dependency for the skill.