brand-co-branding

Warn

Audited by Snyk on Mar 5, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs in "Step 2: Identify and Vet Potential Partners" under "Partner Sourcing Strategies" to explore the Xiaohongshu platform and perform social listening/monitoring of mentions and user-generated content (public third-party content) which the agent would need to read and interpret to select and vet partners, allowing that content to influence decisions and next actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 5, 2026, 11:41 AM