ClawHub
Back to skill

Security audit

Etf Holdings Predictor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed ETF market-analysis helper that fetches public market data and produces non-binding predictions, with no evidence of hidden execution, persistence, credential use, or destructive behavior.

Install only if you want an agent to fetch public ETF and constituent-stock market data and generate short-term directional analysis. Treat outputs as informational, especially any options-related suggestions, and avoid relying on it as investment advice or trade execution guidance.

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
93% confidence
Finding

The trigger phrases in the metadata are broad finance terms such as ETF预测、ETF涨跌、ETF方向、成分股分析 and ETF期权方向, which can match ordinary market discussion rather than a deliberate request to invoke this specific skill. In an agent environment, this can cause unintended activation and autonomous market-analysis behavior in contexts where the user only asked for general commentary, increasing the chance of overreach and inappropriate tool use.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The activation condition mixes several broad intents—price prediction, direction judgment, options exercise direction, and phrases like ‘预测XXX ETF’—without precise invocation boundaries. In this finance context, ambiguous activation is more dangerous because it may trigger detailed predictive analysis and options-related guidance from casual conversation, leading to unintended financial decision support and unnecessary external data access.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.