ClawHub
Back to skill

Security audit

设计走查

Security checks for vulnerabilities and agentic risk

Overview

This skill is a design-compliance reviewer that reads a specified design spec and HTML/CSS files to produce a report, with no executable code or hidden persistence.

Install only if you want an agent to review page files against design guidelines. Expect it to read the selected design-spec Markdown and target HTML/CSS files, and confirm the files before letting it inspect broader project content.

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
95% confidence
Finding

The skill explicitly states it may proactively trigger after generating any HTML/CSS page, even without a clear user request. That broad activation scope can cause unauthorized file reads of design-spec documents and page assets, and may make the agent act on unrelated work context the user did not intend to audit.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation rules instruct the skill to proactively trigger in multiple situations, including asking to run after page generation. In an agent environment, this broadens the skill's authority boundary and can lead to unsolicited analysis, unnecessary access to local files, and execution of workflows the user did not explicitly authorize.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.