Security audit
skill-local-overlay
Security checks for vulnerabilities and agentic risk
Overview
This skill gives a disclosed workflow for safely tracking local edits to installed skills, with no hidden execution or unrelated data access.
Install only if you want agents to help manage local edits to installed skills. Review each proposed patch before applying it, because changing marketplace, connector, or built-in skill instructions can affect future agent behavior.
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.