entity-optimizer

Warn

Audited by Snyk on Feb 21, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly requires using public search results and SERP analysis and to query public knowledge sources (e.g., "Proceed with the audit using public search results, AI query testing, and SERP analysis" and "Query Knowledge Graph API", Wikidata/Wikipedia checks in Step 1 and Data Sources), so the agent will ingest untrusted, user-generated public web content that can materially influence its decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 06:13 AM