Security audit
additive-bias-defense
Security checks for vulnerabilities and agentic risk
Overview
This skill is a benign review checklist that asks agents to question unnecessary code additions and does not run code or request sensitive access.
Before installing, users should understand that this skill may make an agent more conservative about adding code and may ask for evidence before accepting new abstractions or files. It does not appear to add runtime access or automation risk on its own.
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.