ClawHub
Back to skill

Security audit

SurfAgent X

Security checks for vulnerabilities and agentic risk

Overview

This is an instruction-only X automation guide that clearly describes posting and engagement workflows without installing code or hiding extra behavior.

Install only if you trust the separate SurfAgent/X adapter and the logged-in browser session it will use. The skill itself is guidance, but an agent following it may post, reply, like, repost, follow, or switch among available X accounts, so review account selection and public actions carefully.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (1)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
2. like action executes
3. visible state changes to the liked state, or re-extraction confirms the action

Do not claim success from only calling `x_like_post` without checking the resulting state.

## 7. Proof rules
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Static analysis

No suspicious patterns detected.