Security audit
Boring Threads Publisher
Security checks for vulnerabilities and agentic risk
Overview
This skill is a clearly disclosed Threads publishing helper that uses a third-party MCP connector and credential-bearing link to post content the user asks it to publish.
Before installing, understand that the MCP link is effectively a password for the Boring connector and that the skill can publish or schedule public Threads content and upload selected media through Boring. Use it only with a Boring account you trust, keep the connector URL private, and review account, media, and final post text before publishing.
Vulnerability Patterns
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
- Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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.