scientific-writing

Warn

Audited by Snyk on Feb 24, 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's required two-stage workflow explicitly instructs using the research-lookup skill to "gather relevant literature and data" (SKILL.md, "Stage 1: Create Section Outlines with Key Points" and other sections) and also suggests using the public K-Dense Web (www.k-dense.ai), meaning the agent will fetch and interpret open/public third‑party content which will directly drive writing decisions and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 24, 2026, 01:26 AM