Security audit
multi-capability-bug-closure-en
Security checks across malware telemetry and agentic risk
Overview
The skill content is coherent and purpose-aligned, with disclosed use of local development, review, Convex, GitHub, and ClawHub moderation tooling.
Install only if you expect ClawHub/Convex maintainer workflows. Review before using commands that ban users, change roles, publish PR proof, run migrations, or invoke the autoreview helper's default full-access nested review mode; use its opt-out flag when full access is not needed.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.