ClawHub
Back to skill

Security audit

uibc-team-fin

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow UIBC finance-domain judging package with a local self-test script and no evident credential, network, persistence, or data-mutation behavior.

Installers should understand that this is a specialized Chinese-language UIBC finance-domain judging aid, not a general finance or legal compliance tool. It should be invoked only for TH-FIN-001/002 style migration-judgment tasks, and any real financial, legal, or contractual output should still be reviewed by a human as the skill itself states.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The trigger list includes very broad terms such as “金融”, “UIBC”, “记忆迁移”, and “证据包”, which can appear in ordinary discussion and may cause unintended invocation of this skill. In an agent ecosystem, ambiguous activation can misroute tasks, cause inappropriate execution of domain-specific workflows, and create opportunities for prompt/skill-selection manipulation by inserting trigger words into otherwise unrelated content.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger description includes broad, generic keywords such as UIBC, finance, migration judgment, evidence package, and accountability, which can cause the skill to activate in conversations that merely mention these topics. This creates overbroad routing behavior that may invoke the wrong specialized skill, leading to irrelevant compliance-style outputs, confusion, or inappropriate handling of sensitive financial topics.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The markdown usage conditions define activation based on broad topic mentions rather than strict invocation requirements, so ordinary discussion of finance, UIBC, memory migration, or accountability may incorrectly route into this skill. In a security-sensitive agent environment, ambiguous activation expands the attack surface by increasing the chance of unintended skill selection and misapplication of domain-specific authority.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file’s docstring and all user-facing status messages are exclusively in Chinese, which imposes a specific language on users. Under the stated policy, locale-specific behavior should either offer user choice or clearly document a justified regional constraint, neither of which appears in this file.

Content

No source excerpt is available for this finding.