scientific-writing

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: 0.80). The skill explicitly requires using the research-lookup skill to search, extract, and organize literature and data from external/public sources (e.g., public databases like ARCHS4 and web-hosted papers) and even suggests using the external K-Dense Web platform, so the agent will ingest and interpret untrusted third-party web content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:47 PM