audn-vuln-monitor

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to call the external Audn.ai API (base URL https://audn.ai) — e.g., GET /api/results/<result_id> — which returns full transcripts, analyses, and attack details that the agent is expected to read and act on, thus exposing it to untrusted third-party content that could carry indirect prompt-injection instructions.