Historique des audits
market-research-reports - 4 audits
Version de l’audit 4
Dernier SûrJan 17, 2026, 06:16 AM
All 527 static findings are FALSE POSITIVES. The scanner misinterpreted business terminology (SAM=Serviceable Addressable Market), LaTeX commands as cryptographic algorithms, markdown code blocks as shell commands, and standard file paths as path traversal. The only subprocess.run call uses hardcoded arguments to invoke sibling skills with no injection risk.
Facteurs de risque
⚙️ Commandes externes (1)
Version de l’audit 3
SûrJan 17, 2026, 06:16 AM
All 527 static findings are FALSE POSITIVES. The scanner misinterpreted business terminology (SAM=Serviceable Addressable Market), LaTeX commands as cryptographic algorithms, markdown code blocks as shell commands, and standard file paths as path traversal. The only subprocess.run call uses hardcoded arguments to invoke sibling skills with no injection risk.
Facteurs de risque
⚙️ Commandes externes (1)
Version de l’audit 2
Risque moyenJan 12, 2026, 05:05 PM
AI analysis failed after multiple attempts - MANUAL REVIEW REQUIRED before publishing. This skill cannot be auto-published until reviewed by a human.
Facteurs de risque
⚙️ Commandes externes (301)
📁 Accès au système de fichiers (33)
Motifs détectés
Version de l’audit 1
Risque faibleJan 4, 2026, 04:56 PM
Simple script-based visual generator with no data exfiltration or persistence capabilities. Subprocess usage is limited to invoking local generator scripts.