Security audit
Skillguard
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed local API for auditing SKILL.md text and does not show hidden data access, persistence, or destructive behavior.
Before installing, note that this runs a local HTTP service and installs common Python web dependencies. Submit only skill files you intend to analyze, and check that any missing detector modules required by products.skillscan, products.scopecheck, and products.promptguard are available in your environment.
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.