ClawHub
Back to skill

Security audit

get-tldr

Security checks across malware telemetry and agentic risk

Overview

This skill coherently sends a user-provided URL to get-tldr.com for summarization, while using a local API key and keeping a local log that users should understand.

Install only if you are comfortable sending target URLs to get-tldr.com and storing submitted URLs plus returned summaries in a local log. Use a dedicated API key, keep config and .env files private, and configure or regularly clear the logfile if links may contain sensitive query strings or private content.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill declares no permissions, yet its documented behavior includes network access, reading local configuration and environment secrets, and writing persistent log files. This creates an avoidable trust gap: users and policy systems cannot accurately assess that the skill accesses credentials, transmits URLs to a third-party API, and stores data locally.

Tp4

High
Category
MCP Tool Poisoning
Confidence
97% confidence
Finding
The skill claims it only returns the API summary unchanged, but its documented behavior also reads API credentials from local sources and writes persistent logs containing the input URL and API response. This mismatch can expose sensitive URLs, summarized content, and local secret-handling behavior without clear user expectation or consent, increasing the risk of privacy leakage and secret misuse.

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The skill description says it should only provide and format the API output, but the code also persistently logs the submitted URL and the full API response to disk. That can leak sensitive URLs, query tokens, private document locations, or summarized confidential content to local storage without clear user consent, increasing privacy and data-retention risk.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The script sends the user-provided URL to a third-party service, which may expose private internal links, sensitive query parameters, or confidential resource locations. Because the skill description emphasizes returning the summary, users may not realize their input is being transmitted externally unless they inspect the code or docstring.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The code logs both the submitted URL and the API response to a local logfile without clear disclosure in the skill's functional description. This creates an avoidable persistence channel for potentially sensitive inputs and outputs, which can later be accessed by other local users, backup systems, or support tooling.

VirusTotal

41/41 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.