ClawHub
Back to skill

Security audit

FireAnt Stock Price Checker

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public Vietnamese stock or index pages from FireAnt and formats market data, with no evidence of hidden persistence, credential access, destructive behavior, or exfiltration beyond the expected third-party lookup.

Install only if you want a Vietnam-market-specific FireAnt lookup helper and are comfortable sending requested stock symbols to FireAnt.vn through a local headless browser CLI. Treat the returned data as informational market data, and verify financial decisions with authoritative sources.

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
  • 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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The skill description claims broad support for stocks, indices, and rich market statistics, while the documented implementation relies on browser automation and subprocess execution that are not clearly declared as capabilities. This mismatch is dangerous because users and policy systems may authorize the skill under a narrower trust model than what it actually needs, enabling undeclared resource access and misleading downstream use of incomplete or incorrect financial data.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill advertises shell-capable behavior via example commands and references to local executables, but it does not declare any explicit tool scope such as allowed tools or permissions. This is dangerous because it obscures the skill's execution capabilities from the orchestrator and reviewers, increasing the chance that shell or subprocess access is granted implicitly without proper oversight.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The usage pattern maps the broad phrase "How is the market doing today?" directly to VNINDEX, but this wording is common everyday finance chat and does not clearly constrain when this skill should activate versus a more general market-analysis skill. The file does not provide exclusion criteria or negative examples to narrow this trigger.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/check_stock.py (reported line 17)May include surrounding context.

python
def run_agent_browser(args: List[str]) -> str:
    """Run agent-browser command and return output"""
    try:
        result = subprocess.run(
            ['/Users/loc/Library/pnpm/agent-browser'] + args,
            capture_output=True,
            text=True,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest description hard-codes Vietnamese stocks, exchanges, and indices, which creates a locale-specific constraint. While this may be the intended domain, the skill does not explicitly frame this as a region-specific skill choice in its invocation-facing description, which can violate language/locale policy if selected without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file description explicitly states it is for Vietnamese stock price lookup, and the extraction logic relies on Vietnamese page labels throughout the script. This enforces a specific language/locale behavior without any opt-in or configurable language selection.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill automatically opens external URLs on fireant.vn and performs browser/network actions without clearly warning the user that requests will be sent to a third-party service. This can expose user-provided stock symbols and browsing metadata to an external site and reduces informed consent around outbound network activity.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.