Security audit
method-vocabulary-diagnostic
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed academic-writing diagnostic that reads user-provided Method text and bundled reference markdown files to produce vocabulary feedback.
Installers should expect this skill to inspect academic Method text and local reference markdown examples. Only run the optional Windows junction command if you intentionally maintain that D:\method-skill-project directory; otherwise the packaged markdown references are the relevant materials.
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.