Security audit
我的测试
Security checks across malware telemetry and agentic risk
Overview
The skill’s login purpose is understandable, but it asks users to handle plaintext credentials and create a reusable logged-in session file without enough safety boundaries.
Install or run only after inspecting the referenced save_session.py and confirming the exact outbound-system URL and account scope. Treat login_credentials.json and auth.json as secrets, keep them out of source control, restrict file permissions, delete or rotate them when no longer needed, and remember that auth.json may be equivalent to an active login session.
SkillSpector
By NVIDIA
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
VirusTotal
65/65 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.
