Security audit
document-ahead-coding
Security checks for vulnerabilities and agentic risk
Overview
This skill only tells the agent to document non-trivial coding work before implementation, with no hidden execution, credential access, or network behavior.
Installers should expect this skill to make the agent create and maintain planning documents before substantial coding work. Review those docs if they may include sensitive discussion details, but the artifact shows no hidden execution, exfiltration, destructive behavior, or overbroad 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.