Security audit
Retention Policy Planner
Security checks across malware telemetry and agentic risk
Overview
The reviewed skill artifacts are coherent operational/documentation helpers with sensitive actions disclosed and gated by user confirmation or dry-run workflows.
Install only if you intend to use these operational skills in a trusted ClawHub/Convex workspace. Review users should understand that staff moderation, email, production migration, and AI code-review workflows can affect real systems or send code/diffs to selected providers, so keep the documented dry-run and explicit signoff gates in place.
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.