Security audit

Claw Stock

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese stock-analysis skill with no executable code, persistence, credential access, or hidden data movement, though its broad trigger phrasing should be narrowed.

Install this only if you want a Chinese-language stock analysis assistant. Treat its ratings and buy/sell discussion as educational commentary, verify current market data independently, and be aware that ambiguous prompts may route to this skill unless the publisher narrows the trigger wording.

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

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The activation description uses broad phrases like '分析一下', '看看这只', '打个分', and '怎么看', which are common conversational expressions and can cause the skill to trigger in contexts where the user did not intend stock analysis. In an agent environment, over-broad routing can misdirect unrelated requests, suppress better-matched skills, or cause the system to present financial-analysis behavior unexpectedly, which is especially sensitive because it may influence financial decisions.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The example triggers include very broad natural-language phrases like “分析一下”, “看看这只”, and “值得买吗”, which can cause the skill to activate on casual market discussion without a clear stock-analysis request. In an agent environment, overbroad activation increases the chance of unintended routing, causing the model to invoke this skill when the user did not actually request investment-style analysis or when the referenced entity is ambiguous.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The skill content is written to always respond in Chinese and does not provide user-language negotiation or document a strict locale requirement. This can cause misunderstandings, reduce user ability to notice disclaimers or risk statements, and make the agent less safe and usable for users who invoked the skill in another language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: All user-facing instructions, examples, and output are presented only in Chinese, with no indication that other languages are supported or that the user can choose their preferred language. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.