context-engineering

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: 0.80). This skill explicitly instructs research sub-agents (see agents/options-researcher.md and deepen-plan.md) to fetch and analyze public third-party sources such as GitHub repos, company blogs/docs (e.g., "Research how enterprise companies (Stripe, Square)" and "Find top GitHub repos"), so the agent will ingest untrusted/user-generated web content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:25 PM