ClawHub
Back to skill

Security audit

Pc368 Filter Analyzer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed browser-based scraper and calculator for PC368 draw statistics, with no evidence of hidden execution, persistence, credential use, or destructive behavior.

Install only if you are comfortable with an agent opening pc368.net and analyzing gambling-related draw data. The skill does not place bets or use credentials, but its profit/loss calculation should not be treated as financial advice or a guarantee of winnings.

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
95% confidence
Finding

The trigger list includes a catch-all condition such as '类似含义的指令', which makes activation criteria ambiguous and overly broad. This can cause the skill to run unintentionally in response to loosely related user input, leading to unexpected browsing, data retrieval from a third-party gambling site, and actions the user may not have clearly consented to.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill directs the agent to open an external gambling-related website and scrape remote data, but the description and flow do not clearly warn the user about this network access beforehand. Without an upfront notice, users may not understand that the skill will contact a third-party service, exposing them to privacy, compliance, or policy risks tied to gambling content and remote data retrieval.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.