context-manager

Warn

Audited by Snyk on Feb 16, 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 FETCH operation (Operation 2) and related workflows (e.g., "Fetch & Reference" and the "process 'fetch, persist, and reference external context'") call ExternalScout to retrieve live external documentation and persist source URLs, so the agent will fetch and read arbitrary public web documentation.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 11:18 PM