linear

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

• Third-party content exposure detected (high risk: 0.75). Outsider free text can enter the LLM via Linear issue/comment content that the agent reads at runtime through ClawLink’s Linear API (e.g., issue descriptions and comments authored by other users), which is then ingested into the agent context for actions like describing or updating issues.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill requires running "npx @useclawlink/cli" which fetches and executes remote code from the npm package (https://www.npmjs.com/package/@useclawlink/cli) and interacts with the ClawLink service (https://claw-link.dev), so the agent runtime depends on executing externally‑fetched code that controls its operations.