iterative-refinement

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). This skill explicitly instructs the agent to perform web searches and ingest findings from public sites (see web-search-integration.md and README's "Research-Enhanced Usage" with examples like site:github.com and searching official docs), meaning the agent will read and act on untrusted, user-generated third-party content found on the open web.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:03 AM