ClawHub
Back to skill

Security audit

资产底牌｜护城河解剖

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese stock-analysis skill with disclosed financial research behavior and no executable code, persistence, credential use, or hidden data handling.

Install this only if you want Chinese-language listed-company moat analysis. Treat the generated ratings and investment conclusions as research assistance, not personalized financial advice, and avoid uploading confidential documents unless you are comfortable having them processed for this analysis.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README uses very broad natural-language invocations such as asking to analyze a company by name or code, without defining explicit trigger phrases, scope limits, or confirmation boundaries. In an agent environment, this can cause accidental or over-broad activation on ordinary user requests, leading the skill to process sensitive uploaded documents or provide investment-style analysis when the user did not clearly opt into this specific workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown file is entirely written in Chinese and does not indicate that the language choice is optional or restricted to a justified Chinese-language context. Under the natural-language policy rule, forcing a specific language without user opt-in is a locale/language policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The file title and instructions are written as a mandatory Chinese output template, and L03 states that all analysis results must uniformly follow this format. This imposes a specific language/locale requirement without offering the user a choice or documenting why the constraint is necessary, which matches the language-policy violation criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

All user-facing instructions and examples are presented only in Chinese, with no statement that users may choose another language or that the locale restriction is intentional. This can constitute a language-policy issue because the skill appears to force a specific language without documented opt-in or justification.

Content

No source excerpt is available for this finding.