Security audit
stack-mode
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed workflow helper for iterating review or fix commands across stacked pull requests, with no hidden install-time code.
Before installing, understand that commands using this skill can run review or fix workflows across multiple related PRs and post a summary comment on the root PR. This is purpose-aligned, but use it in repositories where you are comfortable with that PR-commenting authority.
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.