Security audit
thinking-circle-of-competence
Security checks across malware telemetry and agentic risk
Overview
This skill is a low-risk reasoning checklist that tells an agent to verify uncertain claims instead of inventing facts.
Installing this should mainly make the agent more cautious about unsupported factual claims. Expect it to ask for evidence, inspect relevant artifacts, or mark uncertainty in higher-stakes situations; no privileged or persistent behavior is disclosed in the inspected file.
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.