ClawHub
Back to skill

Security audit

A股上市公司公告

Security checks across malware telemetry and agentic risk

Overview

This stock-data skill appears purpose-aligned, with the main caveat that one market-data request uses unencrypted HTTP.

Install only if you are comfortable with the skill contacting external stock-market data services. Avoid sending sensitive or proprietary keywords through it, and verify important announcement links or results independently because the HTTP request could be intercepted or altered.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Transmission

Medium
Category
Data Exfiltration
Content
if keyword: payload["searchKey"] = [keyword]

        try:
            resp = requests.post(url, headers=headers, json=payload, timeout=10)
            if resp.status_code == 200:
                data = resp.json()
                results = []
Confidence
78% confidence
Finding
The code performs an outbound request to a third-party service over plain HTTP, which exposes request contents and response data to interception or tampering by an on-path attacker. Even though the payload is low sensitivity, lack of transport security can enable manipulated announcement data, misleading links, or corrupted results to be returned to downstream users or agents.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.