divergent-thinking-scoring

Warn

Audited by Snyk on Apr 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: 0.80). The skill explicitly instructs using the external SemDis web platform (https://semdis.wlu.psu.edu/) and GloVe Common Crawl embeddings (both referenced in SKILL.md and references/scoring-rubric.md) to compute semantic distance, meaning it expects the agent to ingest and act on untrusted public web–sourced content that could influence scoring decisions.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 10:17 AM
Issues
1