sales-temi

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (see Example 2 and references/temi-api-reference.md) explicitly ingests user-provided, third‑party transcripts from the Temi API (GET /jobs/{id}/transcript and media_url uploads) and then uses that content to drive downstream actions (e.g., write to warehouse / pipeline routing), so untrusted user-generated content is read and can influence agent behavior.