Security audit
Action Runner
Security checks for vulnerabilities and agentic risk
Overview
This skill is an action-execution helper that clearly requires dry runs, named targets, and user approval before making external changes.
Install only if you want an agent to prepare and, after approval, execute changes in external tools such as GitHub, Linear, Slack, email, or calendars. Review each dry-run carefully, especially red/high-risk actions like posting, sending, deleting, merging, deploying, or charging, and keep target scopes narrow.
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.