ClawHub
Back to skill

Security audit

GeeLark Complete

Security checks for vulnerabilities and agentic risk

Overview

The skill helps operate GeeLark through local APIs and UI automation, and the sensitive actions it describes are disclosed and bounded by verification and user-intent limits.

Install only if you intend to let the agent operate GeeLark locally. Keep GEELARK_API_KEY private, avoid saving secrets in memory or troubleshooting notes, review actions before any browser/profile or posting workflow, and require explicit confirmation before anything that could affect an external account.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill explicitly documents use of a bearer token in openclaw-config/.env and operational access to a local API, but provides no warning about secret handling, redaction, or avoiding disclosure in logs, terminal output, or published artifacts. In a skill that permits Bash/Read/Write and troubleshooting workflows, this increases the chance that an agent or user will expose credentials during routine use.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill describes UI automation, browser/profile control, asset transfer, and posting workflows that can affect real user accounts or external platforms, yet it does not include a clear warning, confirmation requirement, or safe-use guardrails. Because this is an end-to-end operational runbook with API-first and UI-fallback execution paths, misuse or accidental execution could trigger unintended account actions, content posting, or policy violations.

Content

No source excerpt is available for this finding.