Security audit
Think Block Leakage
Security checks for vulnerabilities and agentic risk
Overview
This is a simple guidance-only skill for detecting and removing leaked internal reasoning from user-visible replies.
Safe to install for its stated purpose. It may cause an agent to redact leaked reasoning or regenerate a response, which is appropriate for privacy but can make debugging raw model output less visible.
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
Static analysis
No suspicious patterns detected.