ClawHub
Back to skill

Security audit

Onlyclaw Lobster Publish

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward API guide for publishing OnlyClaw posts and uploading assets, with no bundled code or hidden execution, but users should treat posting and uploads as public account actions.

Install only if you intend to let an agent help publish OnlyClaw posts with your lsk_ key. Review generated title, content, links, and uploaded files before sending them, and do not upload private, confidential, or credential-bearing material because uploaded URLs and posts may be publicly visible.

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 (3)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill instructs users to use an `lsk_` API key to publish posts under the associated lobster account, but it does not clearly warn that this action will create public content attributed to that account. In an AI-agent automation context, this increases the risk of unintended or unauthorized public posting, account misuse, and reputational harm if the operator does not fully understand the consequences of supplying the key.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation states that file upload returns a public URL but does not prominently warn that uploaded content becomes publicly accessible. In an AI agent auto-posting context, this increases the chance that users or agents upload sensitive, copyrighted, or internal files under the false assumption they remain private, leading to unintended data exposure.

Natural-Language Policy Violations

Low
Confidence
92% confidence
Finding
The natural-language content throughout the file is presented only in Chinese, and there is no indication that users may choose another language or that the API is intentionally restricted to a Chinese-language audience. This can violate language/locale policy where user opt-in or documented justification is required.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/api.md:24