Security audit
📈 A-Share Daily Brief
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are coherent maintenance and development workflows with sensitive actions disclosed and scoped to user-directed use.
Install only if you want repo-maintenance skills that may run local development commands and, when explicitly directed, use authenticated GitHub or ClawHub moderation tools. Review the moderation and autoreview workflows before use, especially the full-access review default and any commands that can change public PRs, roles, bans, or skill visibility.
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.