Back to skill

Security audit

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

Security checks across malware telemetry and agentic risk

Overview

This skill fetches public SEC filing data as advertised, with expected SEC network access and dependency hygiene notes but no evidence of hidden, destructive, or credential-seeking behavior.

Install only if you are comfortable with live requests to SEC services. Configure the SEC User-Agent with appropriate contact information, avoid sensitive personal details there, and prefer pinned or locked dependency versions in controlled environments.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (10)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill clearly instructs the agent to access the SEC EDGAR service and therefore requires outbound network access, yet no corresponding permission is declared. This creates a transparency and policy-enforcement gap: hosts may install or run the skill without understanding that it can make external requests, weakening sandboxing and review controls.

Unpinned Dependencies

Low
Category
Supply Chain
Content
pandas>=2.2.0
pydantic>=2.0.0
requests>=2.28.0
beautifulsoup4>=4.12.0
Confidence
96% confidence
Finding
The dependency is specified with a lower bound only (pandas>=2.2.0), which allows future major or minor releases to be installed without review. This weakens supply-chain control and can introduce breaking changes or newly introduced vulnerabilities into the environment unexpectedly.

Unpinned Dependencies

Low
Category
Supply Chain
Content
pandas>=2.2.0
pydantic>=2.0.0
requests>=2.28.0
beautifulsoup4>=4.12.0
lxml>=4.9.0
Confidence
96% confidence
Finding
Using pydantic>=2.0.0 permits any newer release, including versions not yet tested or security-reviewed for this skill. That increases supply-chain risk because builds are not reproducible and may silently pick up insecure or incompatible versions.

Unpinned Dependencies

Low
Category
Supply Chain
Content
pandas>=2.2.0
pydantic>=2.0.0
requests>=2.28.0
beautifulsoup4>=4.12.0
lxml>=4.9.0
python-dateutil>=2.8.0
Confidence
97% confidence
Finding
The requests dependency is unpinned, so installs may resolve to different versions over time. In a network-facing skill that interacts with external SEC resources, uncontrolled dependency drift increases the chance of importing a vulnerable or behavior-changing release.

Unpinned Dependencies

Low
Category
Supply Chain
Content
pandas>=2.2.0
pydantic>=2.0.0
requests>=2.28.0
beautifulsoup4>=4.12.0
lxml>=4.9.0
python-dateutil>=2.8.0
Confidence
95% confidence
Finding
beautifulsoup4>=4.12.0 does not guarantee reproducible builds and allows unreviewed future versions to be installed. While not directly an exploit by itself, this is a real supply-chain hardening weakness.

Unpinned Dependencies

Low
Category
Supply Chain
Content
pydantic>=2.0.0
requests>=2.28.0
beautifulsoup4>=4.12.0
lxml>=4.9.0
python-dateutil>=2.8.0
Confidence
97% confidence
Finding
lxml is unpinned, which is more concerning than some other libraries because it processes untrusted markup and has a history of parser-related advisories. Allowing arbitrary newer versions reduces assurance that the deployed parser version is known-safe and tested.

Unpinned Dependencies

Low
Category
Supply Chain
Content
requests>=2.28.0
beautifulsoup4>=4.12.0
lxml>=4.9.0
python-dateutil>=2.8.0
Confidence
95% confidence
Finding
python-dateutil>=2.8.0 allows dependency drift and non-reproducible environments. This is a genuine but low-severity supply-chain weakness rather than an immediate exploit.

Known Vulnerable Dependency: pydantic — 3 advisory(ies): CVE-2021-29510 (Use of "infinity" as an input to datetime and date fields causes infinite loop i); CVE-2024-3772 (Pydantic regular expression denial of service); CVE-2021-29510 (Pydantic is a data validation and settings management using Python type hinting.)

High
Category
Supply Chain
Confidence
86% confidence
Finding
The requirement pydantic>=2.0.0 includes versions that may fall within vulnerable ranges for known advisories, and because there is no upper bound or pin, an affected release could be installed. In a data-processing skill, malformed external input could potentially trigger denial of service or validation-path issues if a vulnerable version is resolved.

Known Vulnerable Dependency: requests — 10 advisory(ies): CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +7 more

High
Category
Supply Chain
Confidence
93% confidence
Finding
The requirement requests>=2.28.0 is broad and may resolve to versions affected by one or more cited requests advisories, depending on the exact installed version. Because this skill interacts with external network resources, vulnerabilities in HTTP handling, redirects, proxies, or credential handling could be relevant if the code uses those features.

Known Vulnerable Dependency: lxml — 10 advisory(ies): CVE-2021-43818 (lxml's HTML Cleaner allows crafted and SVG embedded scripts to pass through); CVE-2014-3146 (lxml Cross-site Scripting Via Control Characters); CVE-2021-28957 (lxml vulnerable to Cross-Site Scripting ) +7 more

High
Category
Supply Chain
Confidence
90% confidence
Finding
lxml>=4.9.0 may include vulnerable versions depending on what gets installed, and lxml is a parser library that often handles untrusted markup where parser flaws can matter. In this SEC-filing context, the skill likely processes externally sourced XML/HTML/XBRL, which makes parser-related vulnerabilities more relevant than they would be in a purely local tool.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.