opper-node-agents

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 includes tools that fetch and ingest arbitrary web content (e.g., the fetch_url example in references/TOOLS.md and the search_web/fetchUrl usage in references/COMPOSITION.md by the ResearchAgent), so agents will read untrusted public URLs/search results as part of their workflow, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:03 AM