Security audit
Crowd Prompting
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed marketplace integration for sharing and improving prompt-related text, with real but clearly described risks around public posting and manual remote updates.
Install or update through ClawHub when possible, and review any SKILL.md downloaded directly from the website before replacing your local copy. Treat the API key like a password. Before posting or contributing, assume the text may become public and permanent, and remove secrets, personal data, customer information, proprietary logic, internal system details, and private system prompts or tool specs.
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
63/63 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.