ClawHub
Back to skill

Security audit

uibc-team-uas

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local, dependency-free UIBC judging aid with no evidence of hidden access, persistence, network use, or unsafe execution.

Install only if you need this specific UIBC/UAS judging rubric. Expect Chinese-first outputs and make sure the skill is invoked for TH-UAS-001 or UAS-domain accountability tasks, not generic migration or evidence-package discussions.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The metadata description and read_when/tags define broad trigger phrases such as UIBC, low-altitude economy, migration judgment, evidence package, and accountability without strong exclusion criteria. This can cause the skill to be invoked in loosely related conversations, leading the agent to apply domain-specific judging logic outside its intended scope and produce irrelevant or overconfident guidance.

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 repeats broad, ambiguous activation language and includes generic trigger words that may appear in unrelated contexts. In an agent ecosystem, this increases the chance of accidental routing, which can mislead users, interfere with better-matched skills, and create unreliable accountability outputs based on the wrong domain rubric.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This Python file contains user-facing documentation and runtime output entirely in Chinese, including usage text and status messages, without offering any language selection or opt-in. Under the policy for natural-language violations, forcing a specific language without user choice is in scope for all file types.

Content

No source excerpt is available for this finding.