gtm-enrichment-deep

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

• Third-party content exposure detected (high risk: 0.85). The required workflow calls Sixtyfour/Apollo enrichment endpoints that “browse the web” and return extracted web text (e.g., company website/LinkedIn-derived content) into the agent’s runtime context via the API responses, which can include outsider-authored free text.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill makes runtime POST calls to https://api.gooseworks.ai/v1/proxy/orthogonal/run (via $GOOSEWORKS_API_BASE) to invoke external AI agents (sixtyfour and apollo) that execute enrichment/browsing logic and accept the provided "struct" prompts, so remote agents/ code control the prompts and outputs.