Security audit
Receipt and Expense Reconciler
Security checks across malware telemetry and agentic risk
Overview
The skills are developer and maintainer workflow helpers with some high-impact commands, but the authority is disclosed, scoped to the stated tasks, and paired with user confirmation or verification guidance.
Install only if you trust the publisher for ClawHub/Convex maintainer workflows. Review commands before running moderation, deployment, migration, PR publishing, or full-access autoreview paths, and use dry-run or opt-out flags when you do not want credentials, local files, or remote project state changed.
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.