ClawHub
Back to skill

Security audit

TweetClaw

Security checks for vulnerabilities and agentic risk

Overview

TweetClaw is a disclosed X/Twitter automation skill with meaningful approval, credential, payment, and private-data boundaries.

Install only if you trust Xquik and are comfortable granting an X/Twitter automation plugin the ability to perform approved account actions and paid reads. Keep API keys in OpenClaw config, review the exact post, target, cost, and scope before approving each call, and avoid using it for spam, impersonation, or unauthorized account access.

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 · evals/evals.json (reported line 29)May include surrounding context.

json
"wait for explicit approval"
      ],
      "must_not_include": [
        "post without approval",
        "batch write"
      ]
    },

Static analysis

No suspicious patterns detected.