Audit-Verlauf
scientific-slides - 4 Audits
Audit-Version 4
Neueste Niedriges RisikoJan 17, 2026, 06:46 AM
The skill is a legitimate scientific presentation tool. Static findings are primarily false positives from documentation patterns. Network access is for documented AI image generation with user-provided API keys. Subprocess calls are for local PDF/image operations. No malicious intent or data exfiltration patterns found.
Risikofaktoren
🌐 Netzwerkzugriff (1)
⚙️ Externe Befehle (1)
🔑 Umgebungsvariablen (1)
📁 Dateisystemzugriff (1)
Audit-Version 3
Niedriges RisikoJan 17, 2026, 06:46 AM
The skill is a legitimate scientific presentation tool. Static findings are primarily false positives from documentation patterns. Network access is for documented AI image generation with user-provided API keys. Subprocess calls are for local PDF/image operations. No malicious intent or data exfiltration patterns found.
Risikofaktoren
🌐 Netzwerkzugriff (1)
⚙️ Externe Befehle (1)
🔑 Umgebungsvariablen (1)
📁 Dateisystemzugriff (1)
Audit-Version 2
Mittleres RisikoJan 12, 2026, 04:58 PM
AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.
Risikofaktoren
🌐 Netzwerkzugriff (20)
⚙️ Externe Befehle (421)
📁 Dateisystemzugriff (6)
🔑 Umgebungsvariablen (61)
Erkannte Muster
Audit-Version 1
Mittleres RisikoJan 4, 2026, 04:54 PM
Python scripts handle presentation workflows including file operations, OpenRouter API calls for AI image generation, and optional pdflatex subprocess execution for LaTeX compilation. All capabilities align with the stated purpose of creating scientific presentations. No persistence, obfuscation, or credential exfiltration patterns detected.