x-filter

Warn

Audited by Snyk on Feb 21, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's required workflow explicitly accepts "Manual list
  • User-provided topics/URLs" and "Load materials from x-collect" (see Input and Execution Steps), so the agent ingests arbitrary public URLs/collected web materials and reads them to score and decide next actions, exposing it to untrusted third-party content that could carry indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 05:34 AM