ClawHub

虾皮财务分析大师

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed financial-analysis skill that uses an external DaxiAPI CLI and token, with no evidence of hidden, destructive, or unrelated behavior.

Install this only if you trust the DaxiAPI service and CLI. Prefer a pinned CLI version if reproducibility matters, avoid pasting real tokens into chat, and treat the generated output as financial analysis rather than investment advice.

SkillSpector

By NVIDIA
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
88% confidence
Finding
The trigger list is broad enough to match generic finance-related requests such as ‘财务分析’ or ‘基本面分析’, which can cause the skill to activate outside its intended narrow scope of single-company ROE/DuPont analysis. Unintended invocation can route unrelated user prompts into a workflow that encourages external CLI/API use and structured financial conclusions, increasing the risk of incorrect tool use, overreach, or disclosure of local environment/authentication setup steps.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The ‘When to Use’ section overlaps heavily with broad financial-assistant behavior, not just this skill’s stated purpose. Because the skill instructs the agent to fetch external data and produce analytic reports, overbroad activation criteria make accidental triggering more dangerous in context: the agent may invoke this specialized workflow for ordinary financial questions, leading to unnecessary external access, user confusion, or analysis performed on unverified assumptions.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal