ClawHub
Back to skill

Security audit

investoday-fund-comprehensive-diagnosis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed public-fund analysis workflow that queries market-data APIs and does not show hidden execution, storage, credential access, or mutation behavior.

Before installing, understand that this skill may call the Investoday finance-data dependency when you ask broad fund-analysis or long-term-holding questions. Use it for specific public fund names or 6-digit fund codes, and treat its output as reference analysis 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
  • 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
89% confidence
Finding

The trigger words in the metadata and description are broad user-facing finance phrases such as '基金分析' and '长期持有', which can cause the skill to activate for general investment discussions rather than only explicit fund-diagnosis requests. This increases the chance of unintended invocation, tool use, and overly specific financial analysis in contexts where the user did not clearly ask for this workflow.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The activation scenarios describe common, conversational finance questions without enough scope constraints, so the agent may invoke this skill for ambiguous requests like whether something is suitable to hold long term. In a finance context, accidental activation can lead to unnecessary API calls and responses that appear more authoritative than the user's intent warranted.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.