ClawHub
Back to skill

Security audit

主力建仓扫描

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed China A-share stock scanner that fetches public market data and writes a local report, with no evidence of hidden persistence, credential theft, destructive actions, or exfiltration.

Install only if you want a Chinese-language China A-share screening helper. Expect it to call Eastmoney public market-data APIs and create a local Markdown report. The hard-coded /Users/hushuizhen path and bash-vs-Python command mismatch may need correction before it works on another machine, and the output should be treated as informational rather than investment advice.

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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill invokes an external shell script and writes reports to a workspace file, yet it declares no explicit tool scope or permissions. That mismatch weakens least-privilege controls and can allow broader-than-necessary file and network access if the runtime infers or permits those capabilities implicitly.

Natural-Language Policy Violations

Medium
Confidence
76% confidence
Finding
The skill content is entirely in Chinese and is targeted at沪市/深市主板 stocks, but it does not explicitly state that the locale/language scope is intentional or offer any user opt-in or choice. Under the policy, forced language or locale behavior should be documented and justified if it is region-specific.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrases are broad and common, so the skill may activate for generic investing requests beyond the user's actual intent. Misrouting can cause unintended execution of market-wide scans, unnecessary network/script activity, and responses that override a more appropriate skill or safer manual handling path.

Natural-Language Policy Violations

Low
Confidence
90% confidence
Finding
The entire methodology document is written in Chinese and provides no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Static analysis

No suspicious patterns detected.