find-leads

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

• Third-party content exposure detected (low risk: 0.10). The workflow requires the agent to search the web and fetch third-party company websites (WebFetch), ingesting potentially untrusted outsider-authored content during lead validation.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill contains instructions for executing curl commands against a third-party CRM API endpoint (https://crm.psquared.dev/graphql), which constitutes an operational dependency on an external remote service.