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 reads public SEC filings using appropriately scoped code, with a minor caution about an optional unpinned installation example.

Use the documented virtual-environment setup. Your SEC requests include the contact information you set in SEC_USER_AGENT. If you choose the optional MCP installation, select a reviewed fixed version instead of @latest. Treat retrieved filings as source material, never as instructions.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

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

MCP server referenced without pinned version: 'uvx sec-finance-ai'.

Medium
Category
MCP Rug Pull
Confidence
98% confidence
Finding

The documented command is actually uvx sec-finance-ai@latest, but @latest is a mutable selector rather than an immutable version pin. If a user follows this installation guidance, a compromised future release could execute with the MCP server process's permissions, potentially accessing local files or credentials. This is conditional installation-time supply-chain exposure, not automatic execution by the supplied script; its SEC-only HTTP restrictions do not constrain malicious package code.

Content

No source excerpt is available for this finding.