web-research
Warn
Audited by Snyk on Mar 10, 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.md explicitly instructs the agent to run WebSearch (Step 2) and ingest titles/URLs/snippets from public web pages — and Step 3 even includes Tier 4 sources (forums, social media) — which the agent then uses to build the source map and plan follow-up research, so untrusted third-party content can directly influence decisions and actions.
Audit Metadata