ClawHub
Back to skill

Security audit

A Stock Trading Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed China A-share market assistant that fetches public stock data and gives analysis, with financial-risk caveats but no evidence of hidden access, exfiltration, persistence services, or destructive behavior.

Install only if you want a China A-share focused analysis helper. Verify any market data independently, do not treat generated buy/sell or position-size suggestions as professional financial advice, and be aware that the referenced helper scripts and watchlist files were not present in the inspected artifact.

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
94% confidence
Finding

The manifest trigger is extremely broad and is likely to activate on nearly any A-share-related finance query, causing the skill to take over conversations beyond narrowly scoped stock lookup tasks. In a high-risk domain like trading, over-triggering increases the chance of unsolicited investment guidance, incorrect routing, and the model performing actions or giving advice when the user did not explicitly request this specialized skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description and role definition are written to serve only the China A-share market and present the interaction policy entirely in Chinese, with no indication that users may choose another language. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation unless clearly offered as a choice or justified as a documented locale constraint.

Content

No source excerpt is available for this finding.