tally

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 call Tally’s authenticated APIs (e.g., tally_get_form_details, tally_get_form_responses, tally_list_forms) and ingests the returned form metadata/responses (outsider-authored content from Tally users) as readable text 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 the remote CLI via npx (npx @useclawlink/cli), which fetches and executes code from the npm package (see https://www.npmjs.com/package/@useclawlink/cli and https://claw-link.dev) at runtime, so external code is executed and required for the skill to function.