nda-abgleich

Fail

Audited by Snyk on Aug 1, 2026

Risk Level: HIGH
Full Analysis

HIGH W007: Insecure credential handling detected in skill instructions.

  • Insecure credential handling detected (high risk: 1.00). The skill requires reading user-supplied NDAs and then producing standards and a redlined .docx that include exact/wörtlich formulations and inserted tracked-change text (including the client name), so the LLM must reproduce user-provided confidential content verbatim in its outputs.

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

  • Third-party content exposure detected (medium risk: 0.30). Der Skill liest bei „Modus B — Redlining-Lauf“ den von der Gegenseite bereitgestellten NDA-Entwurf als Eingangsdatei vollständig und erzeugt daraus Word-Tracked-Changes, wodurch outsider-authored Freitext (aus dem übergebenen Entwurf) direkt vom LLM verarbeitet wird.

Issues (2)

W007
HIGH

Insecure credential handling detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
HIGH
Analyzed
Aug 1, 2026, 10:49 AM
Issues
2