ClawHub
Back to skill

Security audit

investoday-fund-risk-analysis

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent fund-risk analysis helper that uses disclosed finance-data APIs and shows no hidden execution, storage, persistence, or trading authority.

Before installing, confirm you are comfortable with the skill sending fund names or codes and the original query to the Investoday finance-data integration for public market-data lookup. Treat its outputs as analytical reference only, not 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
Confidence
91% confidence
Finding
The manifest description lists trigger words such as “回撤” and “波动率” alongside more specific finance terms. These standalone words are broad enough to appear in ordinary financial discussion outside the intended fund-risk-analysis context, and the file does not provide exclusion conditions or negative examples to narrow activation.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The '触发场景' section describes general user intents like asking whether a fund’s risk is high, but it does not clearly distinguish which related requests should invoke this skill versus adjacent skills, except for limited cross-skill notes later. Without explicit non-trigger cases or tighter boundaries, similar fund-analysis queries may match ambiguously.

Static analysis

No suspicious patterns detected.