Security audit
ponytail-review
Security checks for vulnerabilities and agentic risk
Overview
This is a narrow review-style skill that only tells the agent how to flag over-engineered code and does not add executable behavior or hidden access.
Install only if you want a focused over-engineering pass. It is not a substitute for normal correctness, security, or performance review because the skill intentionally excludes those areas.
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.