independent-research

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: 0.90). The SKILL.md explicitly requires using WebFetch and WebSearch to retrieve documentation and community examples from URLs (see "Research Tools" and "Research Protocol" lines that say to "fetch and read" official docs and community examples), so the agent will ingest untrusted public web content that can influence decisions and actions, enabling indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 21, 2026, 01:21 PM