review-management

Warn

Audited by Snyk on Feb 28, 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's workflow explicitly asks for an "App ID (to fetch current reviews)" and instructs the agent to "Read competitor reviews" in SKILL.md, which requires ingesting user-generated, public app-store reviews that could contain untrusted instructions influencing analysis and responses.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 28, 2026, 03:49 AM