bitbucket

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

• Third-party content exposure detected (high risk: 0.75). The required workflow uses ClawLink to browse/read Bitbucket repository contents at runtime (e.g., via npx @useclawlink/cli actions/describe/run bitbucket ...), which can ingest outsider-authored free text from issues/PRs/wiki/comments or repository files 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 runs npx @useclawlink/cli at runtime, which fetches and executes remote code from the @useclawlink/cli npm package (https://www.npmjs.com/package/@useclawlink/cli), a required external dependency that will run code on the agent.