ClawHub
Back to skill

Security audit

run-advanced-patent-query-ip

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly coherent for generating PatSnap patent reports, but its REST image downloader can fetch API-supplied URLs without host validation, so it needs review before use.

Prefer the MCP workflow where possible. If using the REST scripts, only set verified PatSnap endpoints, keep credentials in the execution environment, and run in an environment with outbound network controls until image URL allowlisting and private-network blocking are added.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • 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 (2)

Tainted flow: 'fig_url' from requests.get (line 175, network input) → requests.get (network output)

Medium
Category
Data Flow
Content
if images_dir:
                        # Download a retrieved patent image into the report fixture directory.
                        try:
                            img_resp = requests.get(fig_url, timeout=15)
                            img_resp.raise_for_status()
                            ext = fig_url.split("?")[0].rsplit(".", 1)[-1] or "jpg"
                            local_path = images_dir / f"{pid}.{ext}"
Confidence
96% confidence
Finding
img_resp = requests.get(fig_url, timeout=15)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill explicitly instructs execution of shell scripts, reading environment variables, writing report files, and performing network access, yet it declares no permissions or equivalent capability constraints. This creates a governance gap where a host may under-enforce access controls or users may not understand the skill’s effective authority, increasing the chance of unintended data access, exfiltration, or file writes during execution.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.