Security audit
China Stock Profitgrowth
Security checks across malware telemetry and agentic risk
Overview
The artifacts describe repo-maintenance, Convex, UI proof, review, and moderation workflows with sensitive commands disclosed and generally scoped to user-directed actions.
Install only if you are comfortable with an agent running repo-local ClawHub, GitHub, Convex, and review tooling. Pay special attention before approving moderation writes, public proof publishing, or the autoreview helper's default full-access Codex review mode; use the documented opt-out when you want stricter sandboxing.
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.