soia-pkm-transform-article-learning

Fail

Audited by Snyk on Jul 16, 2026

Risk Level: CRITICAL
Full Analysis

CRITICAL E005: Suspicious download URL detected in skill instructions.

  • Suspicious download URL detected (high risk: 0.70). These are third‑party GitHub repositories (an unofficial NotebookLM CLI and an Open Design repo) referenced as install/clone sources — GitHub code can be legitimate but is an untrusted distribution origin that may include install scripts/CLIs that execute code, so treat them as potentially risky until verified.

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

  • Third-party content exposure detected (high risk: 0.75). NotebookLM provider workflow uploads the user-supplied source (which may be a URL clipped at runtime or other outsider-authored text) into NotebookLM, and that source-grounded content is then read by the LLM to generate artifacts—i.e., runtime ingestion of outsider free text via the “URL/vault/local Markdown → clip/archive → upload source file → NotebookLM generate” path.

Issues (2)

E005
CRITICAL

Suspicious download URL detected in skill instructions.

W011
MEDIUM

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

Audit Metadata
Risk Level
CRITICAL
Analyzed
Jul 16, 2026, 03:01 AM
Issues
2
Security Audit — snyk — soia-pkm-transform-article-learning