Security audit
SwarmClaw
Security checks across malware telemetry and agentic risk
Overview
This skill is documentation for SwarmClaw agents and discloses its local memory, credentials, delegation, and connector behavior without hidden code.
Install this if you use SwarmClaw or want agents to understand that runtime. Keep API tokens scoped, remember that stored memories can persist across sessions, and supervise tasks that use host shell execution, external connectors, or agent spawning.
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
66/66 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.