ClawHub
Back to skill

Security audit

cbismb-harmonyos-publish

Security checks for vulnerabilities and agentic risk

Overview

This skill openly automates publishing HarmonyOS articles to cbismb.com, with no hidden code or persistence, but users should treat it as a live posting tool.

Install this only if you want an agent to post articles to cbismb.com using your logged-in browser session. Review the generated title, body, category, tags, originality setting, privacy checkbox, and comments setting before allowing the final publish action; use the draft option when you are not ready for a live post.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger description is broad enough to activate on ordinary user requests about posting to cbismb.com or the HarmonyOS community, which can cause the agent to move from discussion into performing a live external action without a clearly scoped confirmation boundary. In this skill, that risk is heightened because the action is irreversible or externally visible: it publishes content to a real website using the user's logged-in session.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill does not prominently warn that execution will publish content live to an external website, which undermines informed user consent for a sensitive external side effect. In context, this is more dangerous because the workflow uses an already-authenticated browser session and culminates in pressing a real '发布' button, so a user may think they are asking for assistance or drafting when the agent actually performs publication.

Content

No source excerpt is available for this finding.