Security audit
Function Extraction
Security checks for vulnerabilities and agentic risk
Overview
This skill is a documentation helper that reads user-selected project code and produces implementation notes and diagrams, with no hidden execution or persistence found.
Install only if you are comfortable with the agent reading the relevant project code and producing detailed internal implementation documentation, including file paths, logic, data flow, and possible configuration references.
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.