scientific-slides

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • SAFE (SAFE): No signs of obfuscation, hardcoded credentials, or persistence mechanisms were detected. Subprocess execution in generate_slide_image.py is handled safely using list-based arguments to prevent shell injection.
  • Prompt Injection (LOW): The skill possesses a vulnerability surface for indirect prompt injection because it ingests untrusted PDF and image data which is subsequently processed by an AI model. Evidence:
  • Ingestion points: External PDF files in pdf_to_images.py and image attachments in generate_slide_image.py.
  • Boundary markers: None; content is processed without delimiters or system-level warnings to the model.
  • Capability inventory: The skill can write to the file system (creating PDFs/images) and make network requests to AI providers.
  • Sanitization: No validation or sanitization is performed on the content extracted from processed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 04:47 PM