ClawHub
Back to skill

Security audit

uibc-team-ene

Security checks for vulnerabilities and agentic risk

Overview

This is a narrow UIBC energy-domain judging skill with a small local checker and no evidence of hidden access, persistence, exfiltration, or destructive behavior.

Install only if you need the UIBC ENE-domain TH-ENE-001 judging workflow. Expect Chinese-first output and keep invocation limited to the stated migration-judging/accountability context; the package does not show hidden network, credential, persistence, or destructive behavior.

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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list is very broad and activation guidance is minimal, which can cause the skill to be invoked in contexts that only loosely match terms like UIBC, energy/power, migration judgment, or evidence packages. In an agentic environment, over-broad triggering can route unrelated tasks into governance or adjudication logic, increasing the chance of incorrect outputs, misuse of embedded scripts, or unintended expansion of the skill’s operational scope.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The metadata description and read_when triggers are broad enough that ordinary discussion of UIBC, energy/power, migration judging, evidence, or accountability could invoke the skill even when the user did not intend to use this specialized rule set. Over-broad activation can cause inappropriate routing, policy confusion, or untrusted skill selection in multi-skill environments, especially because the skill positions its own file as an authoritative source and directs downstream behavior.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The '何时用' section repeats ambiguous trigger phrases like mentions of UIBC, energy/power, migration, evidence packages, and accountability without requiring a precise invocation boundary. In an agentic system, such fuzzy matching can unintentionally steer tasks into this skill, producing incorrect evaluations or giving undue authority to this domain-specific judging framework.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This code file contains user-facing natural language in the module docstring and later emits Chinese-only status/output text. Under the policy, forcing a specific language without user choice is a natural-language policy violation unless the locale constraint is explicitly documented and justified, which is not present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script prints all failure, summary, and conclusion messages in Chinese only, which imposes a fixed locale on users. The file does not provide an opt-in mechanism or explain a justified locale restriction, so this matches the language/locale policy violation criteria.

Content

No source excerpt is available for this finding.