Security audit
evidence-first
Security checks across malware telemetry and agentic risk
Overview
This skill only instructs the agent to be careful about evidence and uncertainty, with no hidden code or privileged behavior found.
Installers should expect this skill to make agents show evidence and uncertainty for important claims; it may make analytical outputs more structured, but the artifacts do not show sensitive access or hidden behavior.
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.