ClawHub

A股-加密货币-定时早报-多维度指标全方位分析-安装即用无复杂配置-自带验证降低幻觉

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed market-analysis helper with optional data-fetching scripts, not an automated trading or data-exfiltration tool.

Install only if you want a structured A-share and crypto research assistant. Treat outputs as research, not investment advice; review the Python dependencies before running helper scripts; expect outbound calls to market-data providers; and use a low-risk CryptoPanic token only when news fetching is needed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)

subprocess module call

Medium
Category
Dangerous Code Execution
Content
# Install deps
    subprocess.check_call([str(py), "-m", "pip", "install", "-U", "pip"])
    subprocess.check_call([str(py), "-m", "pip", "install", "-r", str(req)])

    print("ok")
    print(f"venv: {venv_dir}")
Confidence
79% confidence
Finding
subprocess.check_call([str(py), "-m", "pip", "install", "-r", str(req)])

Tainted flow: 'url' from os.getenv (line 573, credential/environment) → requests.get (network output)

Critical
Category
Data Flow
Content
f"auth_token={token}&public=true&currencies={base_symbol}&kind={kind}"
    )
    try:
        resp = requests.get(url, timeout=10)
    except requests.RequestException:
        raise RuntimeError("CryptoPanic request failed") from None
Confidence
94% confidence
Finding
resp = requests.get(url, timeout=10)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger list is very broad and overlaps with ordinary finance discussion, making accidental invocation plausible. In an agent environment, unintended activation can change system behavior, cause irrelevant market-analysis prompts to override user intent, or unnecessarily route sensitive user content into a skill with strong output constraints.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The description says to 'immediately load this skill' for a very broad set of common finance-related phrases, which can cause the skill to activate in contexts where the user did not intend tool-backed market analysis. Overbroad auto-triggering is dangerous because it can expand the skill's reach to more conversations, increasing the chance of unnecessary network calls, script execution, or disclosure of trading-style advice in the wrong context.

Vague Triggers

Medium
Confidence
82% confidence
Finding
The when-to-use section relies on generic keyword mentions like 行情, 策略, 个股, 币对, and similar English finance terms, without requiring clear contextual constraints. In a shared agent environment, ambiguous keyword-driven routing can misfire on incidental mentions, causing the model to adopt this skill's rigid instructions and potentially invoke external resources unnecessarily.

Missing User Warnings

Medium
Confidence
82% confidence
Finding
The skill performs credential-bearing outbound requests to a third-party service using a user-supplied environment token, but there is no user-facing disclosure at the call site or runtime that the token will be transmitted off-box. In an agent skill context, this matters because users may not realize that enabling optional news functionality causes external API use with their credential.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal