agentic-enrollment

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

• Third-party content exposure detected (low risk: 0.10). The skill instructs the agent to fetch external resources over HTTP using inflow aep fetch, which can return arbitrary outsider-authored content read directly by the LLM.

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

• Potentially malicious external URL detected (high risk: 0.70). The referenced installation URLs point to arbitrary domain inflowcli.ai, which lacks strong official enterprise provenance and represents a third-party hosted installer script.