ai-engineering

Warn

Audited by Snyk on Apr 2, 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 required workflows explicitly call external retrieval tools (e.g., the SKILL.md agent_loop uses tools [search_tool, read_page_tool] and references/examples.md defines ResearchAgent with WebSearch/FetchDocument/ExtractContent), meaning the agent ingests open web/public documents and uses those results to drive planning and tool decisions — creating a clear avenue for indirect prompt injection.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 2, 2026, 05:55 PM
Issues
1