ClawHub
Back to skill

Security audit

能力产品化自检

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Chinese-language workflow for evaluating whether personal capabilities can become paid offers, with only narrow local file and optional script use.

Install this if you want a Chinese-language assistant workflow for turning personal skills into testable paid offers. Be aware that its labels and outputs are Chinese, and only run the optional evaluator on JSON input files you intentionally provide.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill instructs the agent to read a local reference file, which implies file-read capability, but it does not declare any explicit tool scope or permissions boundary. This creates ambiguity about what files may be accessed at runtime and increases the risk of over-broad file access if the platform grants default or inherited capabilities.

Vague Triggers

Medium
Confidence
96% confidence
Finding
The description includes broad trigger phrases such as '我能卖什么', '把技能变产品', and '能力变现方向', which are common everyday expressions and may cause the skill to be invoked when the user did not intend to use it. Unintended invocation can route user requests into an overly specific workflow, causing confusion, irrelevant guidance, or accidental exposure of user context to the skill.

Natural-Language Policy Violations

Medium
Confidence
87% confidence
Finding
All user-facing instructions and examples are written only in Chinese, and the skill name/description provide no indication that language choice is optional or that the skill is intentionally limited to a Chinese-speaking context. This can violate language/locale policy when a skill implicitly enforces one language without user opt-in.

Natural-Language Policy Violations

Low
Confidence
88% confidence
Finding
The skill metadata presents the display name and description in Chinese, but the default prompt is hard-coded in English. This creates a language/locale policy concern because the skill appears to force a specific language for execution without documenting user opt-in or providing a language choice.

Natural-Language Policy Violations

Low
Confidence
94% confidence
Finding
The classification results are hard-coded in Chinese (`待验证`, `先验证需求`, `先沉淀交付`, `可服务化，产品化提效不足`, `可优先产品化`). This enforces a specific language in user-visible output with no opt-in, configuration, or documented locale restriction, matching the language/locale policy concern.

Static analysis

No suspicious patterns detected.