Security audit
writing-plans
Security checks for vulnerabilities and agentic risk
Overview
This skill is a planning guide that reads project context and writes implementation plans, with no hidden code or unrelated behavior found.
Before installing, understand that this skill will encourage your agent to inspect project files, write plans under docs/plans, and make frequent git commits as part of an implementation workflow. It does not contain executable code or hidden data handling, but you should still review proposed commits and any subagent execution handoff before proceeding.
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.