anti-ai-detection-writing-skill

Warn

Audited by Snyk on Nov 20, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (low risk: 0.10). The required workflow reads outsider-authored discussion questions and replies (SKILL.md [32], [130], [75]) only for a public thread the user selects, so the agent must fetch that specific content and the attacker cannot force delivery.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (medium risk: 0.30). The operational dependency is the instructed setup download of the Desklib ai-text-detector-v1.01 model weights from Hugging Face, which the local scorer then loads and executes; Desklib is not established as a first-party vendor, and only the self-maintained SHA-256 pins and immutable revision support its provenance, so I assign medium under the recall-first rule.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 20, 2026, 08:32 AM
Issues
2