Security audit
Outfeed Social Manager
Security checks for vulnerabilities and agentic risk
Overview
This skill openly connects an agent to Outfeed so the user can draft, schedule, and publish social media posts, with no hidden files or scanner-backed issues found.
Install this only if you trust Outfeed and the npm MCP package it launches. Use a revocable API key if available, connect only the accounts you want the agent to manage, and verify every post, target account, timezone, and bulk schedule before approving publication.
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.