prompt-engineering

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: 1.00). The skill explicitly includes tool usage that reads arbitrary web pages (e.g., the "read(url)" tool in Scenario 1 / ReAct examples) and a meta-prompting example that scrapes Twitter threads, so it clearly ingests untrusted, user-generated third-party content as part of the agent's workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:50 AM