recognizing-deception

Warn

Audited by Snyk on Jul 27, 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). This skill’s workflow includes “Reading External Sources” (fetching URLs from the public web at runtime via curl) and that fetched page text becomes readable Markdown inserted into the agent’s LLM context, which is outsider-authored free text (public web content).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 27, 2026, 08:23 PM
Issues
1
Security Audit — snyk — recognizing-deception