ClawHub
Back to skill

Security audit

structure-check

Security checks for vulnerabilities and agentic risk

Overview

This skill performs local code checks consistent with its purpose, though its automatic checks may add work after coding tasks.

Expect automatic checks after coding tasks and possible follow-up fixes. Keep checklist entries tied to your requested work, review proposed changes, and use tests alongside these structural checks because their results cannot establish overall correctness.

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)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
`scripts/structure-check.mjs` 随本技能分发，`<skill-path>` 指本技能安装目录。agent 只允许调用脚本并**逐字转述** `STRUCTURE CHECK` 输出块，无权改判结果。

The activation rule covers every completed coding task and treats the generic status phrase "feature implemented" as a trigger.

Medium
Category
Trigger Abuse
Confidence
88% confidence
Finding

The skill activates after every coding task and on a generic completion phrase, rather than requiring an explicit request or project-level opt-in. Activation introduces mandatory checklist creation, script execution, and potentially further code changes, while declaring the script's verdict authoritative; this can extend the agent's workflow beyond the user's intended scope. The legitimate verification purpose and absence of visible exfiltration instructions reduce concern, but do not address the overly broad activation boundary.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.