brilliant-directories

Warn

Audited by Snyk on Apr 29, 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's SKILL.md shows Membrane actions like "Search Posts", "Get Post", "Search Reviews", and "Get Review" that fetch forum posts, blog articles, and reviews (user-generated content) from Brilliant Directories, and the workflow instructs the agent to run and interpret those results via the Membrane CLI, allowing external content to influence actions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 29, 2026, 02:18 PM
Issues
1