deep-research

Warn

Audited by Snyk on Mar 7, 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). This skill explicitly mandates web searches and fetching of third-party pages as part of its core workflow (e.g., SKILL.md's mandatory "LANDSCAPE SCAN" and "RECENCY PULSE" steps and references/agent-templates which instruct "WebFetch top 2-3" and provide a URL fallback via r.jina.ai and git clone), so it ingests untrusted public content that the agent is expected to interpret and use to drive decisions and follow-up actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 05:04 AM