ClawHub
Back to skill

Security audit

measurement-verification

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent maintenance skill for checking and preserving a local measurement/verification system, with no evidence of hidden execution, exfiltration, or deceptive behavior.

Install this only if you use the referenced WorkBuddy measurement and maintenance files. Before running the suggested scripts or recreating the 22:30 automation, confirm the local paths and review any changes to RULES, MAINTENANCE, CAPABILITY, TODO, USER, or daily logs.

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
90% confidence
Finding

The description declares trigger phrases such as “一致性检查”, “度量体系”, and “收工保底” as activation cues, but it does not provide exclusion conditions, narrow context, or negative examples. These phrases are broad enough to appear in ordinary discussion about maintenance work, which could cause unintended invocation of the skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The manifest description and operational guidance are written to operate in Chinese terminology and trigger phrases, with no indication that users may choose another language or that the locale restriction is required. This can violate language/locale policy when a skill implicitly mandates one language without opt-in.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.