Magyar Formázás
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are disclosed maintainer and Convex workflow helpers with some powerful actions, but those actions are purpose-aligned and gated by user direction or verification steps.
Install this only in a ClawHub/Convex maintainer environment where you are comfortable letting the agent use repo tooling, GitHub, Convex, and staff credentials. Review commands before account-moderation, publishing, migration, or full-access autoreview actions, and use dry-run or opt-out controls where available.
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.