ClawHub
Back to skill

Security audit

jav-lookup

Security checks for vulnerabilities and agentic risk

Overview

This skill is not a backdoor, but it should go to Review because it tells agents to find and return adult-content magnet links and download guidance with broad triggers and little user protection.

Install only if you intentionally want a JAV-specific lookup helper and are comfortable with it searching adult-content sites. The magnet-link workflow should be treated carefully because it may involve legal risk, unsafe files, and third-party sites; safer use would limit the skill to metadata from official or reputable sources and avoid returning download links.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill explicitly instructs the agent to search for, extract, and return magnet links from a third-party site, including preferred versions and download guidance. This materially facilitates acquisition of copyrighted adult content and may expose users or downstream systems to legal, malware, and unsafe-content risks, especially since it normalizes visiting aggregation sites and acting on untrusted magnet URIs without any warning or gating.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger description is broad enough to match generic phrases like 查影片信息 or 找磁力链接, which increases the chance the skill is invoked outside a narrowly intended context. Because this skill is designed to retrieve adult-content metadata and potentially piracy-related links, accidental invocation can route unrelated queries into a high-risk workflow and produce inappropriate or policy-sensitive output.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The note requires plot descriptions to use Traditional Chinese because of assumed user preference, but it does not ask the user or provide a language option. This is a natural-language locale policy issue because it forces a specific language without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.