Back to skill

Security audit

Pc368 Probability Predictor

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently performs PC368 draw-data scraping and probability-style prediction, but users should be aware it opens a third-party gambling-adjacent site and uses broad triggers.

Install only if you intentionally want PC368-related prediction analysis. Treat the output as statistical entertainment rather than betting advice, and expect the skill to open pc368.net in a browser to retrieve live draw data. Consider narrowing its triggers to require an explicit PC368 phrase before use.

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
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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

Several triggers such as '分析走势', '预测下一期', and '概率预测' are broad enough to overlap with ordinary analytical conversation, increasing the chance of accidental invocation. Because this skill then opens a third-party site and performs gambling-related analysis, an unintended trigger can expose users to unexpected external access and regulated/high-risk content.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The catch-all trigger phrase '类似含义的指令' is overly ambiguous and can cause the skill to activate on loosely related user requests. In this skill, unintended activation is more dangerous because execution leads to live scraping of an external gambling-related site and generation of betting-style predictions without explicit user confirmation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill initiates live retrieval from https://pc368.net/ and interacts with gambling-related results data, but the description and workflow do not clearly warn users beforehand. This lack of disclosure undermines informed consent and increases risk because users may unknowingly trigger external browsing and gambling-adjacent predictive behavior.

Content

No source excerpt is available for this finding.