ClawHub
Back to skill

Security audit

装修环保避坑

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language renovation environmental-advice skill with no executable code, persistence, credential access, or hidden data behavior, though its advice is opinionated and should not replace professional testing or medical guidance.

Install only if you want strong Chinese-language renovation pollution advice. Treat it as consumer guidance, not a substitute for qualified indoor air testing, code-compliant construction advice, or medical evaluation for symptoms.

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
95% confidence
Finding

The trigger list includes broad, common terms such as “甲醛”, “壁纸”, and “木地板”, which are likely to appear in many general home-improvement conversations and can cause the skill to activate when the user did not explicitly ask for this specific skill. Over-broad activation increases the chance of unintended routing, irrelevant responses, and prompt-scope confusion, especially because the skill enforces a rigid response style and prescriptive flow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This markdown file presents all guidance exclusively in Chinese and does not indicate any user language selection, alternative locale, or justified region-specific scope. Under the policy for natural-language violations, forcing a specific language without user opt-in is in scope.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The referenced section gives symptom-based guidance implying occupants can infer formaldehyde contamination from physical symptoms and then act on that assumption, while also asserting that 'the only method is ventilation' without recommending professional indoor air testing or medical evaluation. Health symptoms like dizziness, cough, infertility concerns, or pet illness are nonspecific, so this advice can cause users to miss other medical or environmental causes or delay appropriate professional help.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.