Security audit
skill-builder
Security checks for vulnerabilities and agentic risk
Overview
This skill coherently helps users create and validate agent skills, with disclosed local file access and user-controlled installation steps.
Before installing, be aware that this skill can guide an agent to read local project guidance and create or migrate files under a skills directory. Review generated SKILL.md files carefully, especially any allowed-tools grants or commands that can publish, delete, push, or call external APIs.
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.