icp-identification

Warn

Audited by Snyk on Jul 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: 0.75). SKILL.md Phase 1: Research instructs the agent to “research it using web tools” when the user provides a company URL, which can fetch public web pages and ingest their readable text into the LLM context for synthesis (public web content → runtime web research → LLM).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 10, 2026, 03:06 PM
Issues
1
Security Audit — snyk — icp-identification