Security audit
Door-in-the-Face Technique
Security checks across malware telemetry and agentic risk
Overview
The artifacts are coherent agent skills for Convex, ClawHub moderation, documentation, and review workflows, with privileged actions disclosed and gated by user confirmation.
Install only if you expect these skills to help an agent operate on Convex and ClawHub repositories. Several workflows can affect production data, public moderation state, user accounts, or staff email, so keep admin tokens restricted and require human review before running commands with --yes, --apply, --send, deploy, or production targets.
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.