giphy

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

• Third-party content exposure detected (high risk: 0.85). The required workflow uses ClawLink to call Giphy at runtime (e.g., actions/describe/run giphy ...), which fetches and ingests GIPHY’s public content/results (outsider-authored free text/metadata) into the agent’s LLM context.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill requires running npx @useclawlink/cli (fetching and executing the remote npm package https://www.npmjs.com/package/@useclawlink/cli) at runtime, which downloads and runs external code as a required dependency.