Security audit
Confirmation Bias
Security checks across malware telemetry and agentic risk
Overview
This is a markdown-only critical-thinking skill that coaches users to test claims against disconfirming evidence, with no executable behavior or privileged access.
This skill is appropriate if you want an agent to slow down confident decisions and ask for falsification tests, counter-evidence, and review triggers. Expect it to ask structured follow-up questions; review external reference links before relying on them as current factual sources.
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.