Security audit
AI绘画提示词优化器
Security checks across malware telemetry and agentic risk
Overview
The artifacts are coherent developer and ClawHub staff workflow skills with disclosed high-impact admin actions and explicit confirmation/audit safeguards.
Install only if you are working on ClawHub or Convex development workflows and understand that some skills can guide staff-level actions such as banning users, sending official email, transferring packages, or running production migrations. Keep admin credentials restricted, review every generated command before running it, and rely on the documented dry-run, confirmation, backup, and audit-log steps for any write or production action.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.