descript-api

Warn

Audited by Snyk on Mar 14, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly imports media from publicly-accessible URLs and directs the agent to "Read transcript — Use GET /published_projects/{slug}" (share.descript.com) as part of the Social Clip Creation Workflow, so the agent ingests public/user-generated third-party content that is used to craft prompts and drive editing actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 14, 2026, 07:07 PM
Issues
1