scientific-slides
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, code obfuscation, or data exfiltration attempts were found in the provided files. The skill adheres to established development practices for scientific workflows.
- [COMMAND_EXECUTION]: The skill utilizes subprocess.run in several scripts (e.g., generate_schematic.py, generate_slide_image.py, validate_presentation.py) to invoke local helper scripts and standard utilities such as pdflatex. These operations are part of the core functionality for building and verifying presentation files and do not use untrusted input in a shell context.
- [EXTERNAL_DOWNLOADS]: The scripts generate_schematic_ai.py and generate_slide_image_ai.py make network requests to openrouter.ai to access LLM services. This is a well-known and legitimate service required for the skill's AI-powered generation features.
- [PROMPT_INJECTION]: The skill is a consumer of user-provided descriptions which it passes to external LLMs. While this constitutes a standard indirect prompt injection surface, the risk is mitigated by the use of structural prompt templates, and no adversarial injection patterns were found in the source content.
Audit Metadata