ClawHub
Back to skill

Security audit

SEC Data Pull Forms 10K, 10Q, 8K and others fillings for companies and stocks - Finance

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed SEC EDGAR finance-data tool whose command execution, dependency install, and SEC network access fit its stated purpose.

Install only if you are comfortable with a skill creating a local Python virtual environment, installing the pinned dependencies, and contacting SEC EDGAR. If you set SEC_USER_AGENT, it may include your contact email and will be sent to SEC servers as intended.

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
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill invokes a local Python CLI, creates a virtual environment, installs dependencies, uses environment variables, and performs outbound network access to SEC domains, but the manifest does not declare an explicit tool scope such as permissions or allowed-tools. That mismatch weakens enforcement and review because a host may grant broader capabilities than reviewers or users expect, increasing the risk of unintended code execution, environment access, or network use.

Content

No source excerpt is available for this finding.

Dynamic import via __import__()

Medium
Category
Dangerous Code Execution
Confidence
75% confidence
Finding

Dynamic import() can load arbitrary modules at runtime, bypassing static analysis and potentially importing malicious code.

Content

Scanner excerpt · scripts/cli.py (reported line 60)May include surrounding context.

python
logging.basicConfig(level=logging.WARNING)
    sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
    try:
        module = __import__(MODULE)
    except ImportError as e:
        print(f"Missing dependency ({e}). Set up the skill first:\n  {SETUP}", file=sys.stderr)
        return 2

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The docstring says the method runs a comprehensive self-test of all tools, but the test list includes calls to interfaces that do not exist as implemented or use contradictory calling conventions. In particular, the self-test calls get_filing_content("AAPL") while the exported wrapper defaults filing_type to '10-Q', and it references methods such as get_available_metrics/get_filing_content as if they are part of the validated 23-tool suite despite the test matrix not matching the actual callable surface cleanly.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The docstring’s user-facing examples and testing instructions are written entirely in English and present expected interaction phrasing only in English, with no indication that other languages are supported or that language choice is user-driven. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.