Security audit
ia-orchestrating-swarms
Security checks across malware telemetry and agentic risk
Overview
This skill is a disclosed multi-agent workflow guide whose background agents and local coordination files fit its stated orchestration purpose.
Install this if you want Codex to coordinate multiple agents for larger reviews or implementation pipelines. Before using it, be aware it may create local ~/.claude team/task state and spawn background teammates, including writable agents when asked; use the documented file ownership, worktree isolation, shutdown, and cleanup steps for work that modifies code.
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.
Static analysis
No suspicious patterns detected.