Security audit
twitter-research
Security checks for vulnerabilities and agentic risk
Overview
This skill is a disclosed read-only Twitter/X research wrapper that uses SELAT paid API calls only after a dry run and user approval.
Before installing, understand that this uses an external SELAT CLI and can spend USDC from your own Circle Agent Wallet for live Twitter/X reads. Use the required dry run to review quoted prices, proceed only if you trust the SELAT CLI and payment flow, and do not paste private keys into the agent.
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.