环评知识库提炼
Security checks across malware telemetry and agentic risk
Overview
This skill locally converts a user-chosen environmental report into CSV/text outputs, with ordinary file-writing caveats and no evidence of hidden network, credential, or background behavior.
Install only if you are comfortable with a local Python tool reading the report file you provide and writing extracted data into the output directory. Use a dedicated empty output folder to avoid overwriting same-named CSV or text files, and review generated files before sharing because they may contain sensitive project information or imperfect extracted data.
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
63/63 vendors flagged this skill as clean.