Practitioner Research Skill

Warn

Audited by Snyk on Mar 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: 0.80). The skill's Evidence Collection and Session Types explicitly require using public GitHub repos and performing "Literature search — Find and cite prior art" and fact-checking web sources/DOIs (e.g., "Portfolio evidence — Public GitHub repos" and the Citation/Fact-Checking sections), which instruct the agent to ingest open/public third‑party content that could influence research decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 10, 2026, 03:56 AM