x-algo-engagement

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.70). This skill processes user-generated social media content—see "Input: User history + candidate posts" in the PhoenixScorer section of SKILL.md—so the agent would read untrusted third-party posts and could be exposed to indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:39 PM