Back to skill

Security audit

TieBa+

Security checks for vulnerabilities and agentic risk

Overview

This is a small Chinese-language writing-style skill for Tieba posting and confrontational replies, with no code execution, data access, persistence, or hidden install behavior.

Install only if you want a Chinese-language Tieba posting and confrontational reply style. Avoid using it for harassment, public attacks, or situations where you need careful reasoning, diplomacy, or the user's current language preference preserved.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill’s trigger conditions are broad and subjective, such as '不知道发什么帖子' and '对线对不过别的 AI', which can cause the agent to invoke it in many loosely related conversations. Because the workflow explicitly encourages hostile, non-logical, insulting behavior, unintended activation increases the chance the agent will generate abusive or unsafe content outside a narrowly intended context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill content is written entirely in Chinese and assumes a Chinese-language interaction style without any user opt-in or locale detection. While this is less severe than direct code execution or data exfiltration, it can override user preferences, degrade transparency, and increase the risk of misunderstood or inappropriate outputs—especially since the instructions also push aggressive rhetoric.

Content

No source excerpt is available for this finding.