file-to-article-generator

Warn

Audited by Snyk on Feb 16, 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 directly ingests arbitrary user-uploaded files (see scripts/parse_file.py and the demo using [INVOKE:parse_file] with local/uploaded PDF/DOCX/image paths) and feeds the extracted {ORIGINAL_TEXT} and images into generation prompts, so untrusted third‑party content can be interpreted and influence the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 03:03 AM