ClawHub
Back to skill

Security audit

SurfAgent X

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent X/Twitter automation guidance skill that emphasizes account and result verification, with no bundled code, persistence, or hidden behavior found.

Before installing, understand that this skill helps an agent operate a logged-in X account and may support public actions if you ask for them. Use it only with accounts you intend the agent to control, and review user-facing posts, replies, follows, reposts, likes, or community joins when those actions matter.

A.I.G

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

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
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.

Content

Scanner excerpt · SKILL.md (reported line 104)May include surrounding context.

md
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

Static analysis

No suspicious patterns detected.