servicem8

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

• Third-party content exposure detected (medium risk: 0.65). At runtime the skill uses ClawLink to log into and query Servicem8 (e.g., listing actions/describing inputs and running actions), which can cause the agent to ingest Servicem8-provided free-text fields (tickets, comments, descriptions) authored by other people; this is outsider-authored content flowing into the LLM via the Servicem8/ClawLink API responses.

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" (which fetches and executes remote code from the npm registry/ClawLink) and references https://claw-link.dev, so a runtime external package is fetched and executed and is a required dependency.