Security audit
claw-prompt-injection-guard
Security checks across malware telemetry and agentic risk
Overview
This is an instruction-only defensive skill that teaches the agent to treat external content cautiously and ask before sensitive actions.
Installing this skill should make the agent more cautious when reading webpages, emails, search results, comments, and documents. Expect extra pauses or confirmation prompts before sending messages, running commands, writing files, accessing sensitive files, installing software, or sending data to external services.
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
58/58 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.