ClawHub
Back to skill

Security audit

uibc-team-ind

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent UIBC judging helper with a local criteria file and checker script, with no evidence of hidden access, persistence, credential use, or destructive behavior.

Install this if you need the UIBC industrial OT TH-IND-001 judging workflow. Treat it as Chinese-first and invoke it only for UIBC/IND-domain judging, not for general OT safety, legal, financial, or accountability advice without human review.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill documentation is entirely in Chinese and does not provide an alternate language or explicit language-selection mechanism. For agents or operators that default to English, this can cause misinterpretation, incomplete execution, or failure to notice critical constraints, which is especially risky because the skill governs validation, evidence, and responsibility workflows in an industrial/OT competition 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 document is predominantly written in Chinese and presents the core package description, contents, and safety statements only in Chinese. Although an English quick-start appears later, the main documentation does not clearly offer a user-selectable language option, which can constitute a language/locale policy issue.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill metadata and description include many broad trigger terms such as UIBC, 工业OT, 迁移判定, 记忆迁移, 证据包, and 责任归属 without narrow gating conditions. This can cause the skill to activate in unrelated conversations, leading to context hijacking, inappropriate delegation, or accidental use of rigid domain-specific judging logic where it does not belong.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The '何时用' section gives ambiguous activation guidance based on loosely related topics and trigger words, including cross-domain review scenarios, without defining boundaries or disambiguation steps. In an agent system, this increases the risk of unintended invocation and over-application of this skill's constraints and outputs to tasks outside its intended competition-evaluation scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The module docstring, usage text, comments, and later user-facing output strings are all written only in Chinese, which imposes a specific language on users without any opt-in or alternative. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless clearly documented as region-specific or optional.

Content

No source excerpt is available for this finding.