ClawHub
Back to skill

Security audit

uibc-team-dat

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow UIBC judging aid that reads its bundled criteria file and runs a local checker, with no evidence of hidden access, persistence, network use, or destructive behavior.

Install only if you want a UIBC DAT-domain judging helper. Be aware that its trigger wording is broad, so agents may apply this formal TH-DAT-001 framing to loosely related requests unless the user or agent narrows when it should be used.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions in the metadata description are broad and topic-based, causing the skill to activate on generic mentions such as UIBC, data elements, migration judgment, or accountability. Over-broad invocation increases the chance of unintended routing, which can misapply this skill’s domain-specific rules to unrelated user requests and produce incorrect or overconfident governance judgments.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The '何时用' section repeats broad activation logic based on simple mention of topical keywords rather than clear user intent, making accidental activation likely. In a judgment/accountability skill, misrouting is more dangerous because it can attach formal-sounding criteria, evidence expectations, or responsibility language to contexts where they do not belong.

Content

No source excerpt is available for this finding.