Security audit

Sitemap Generator

Security checks across malware telemetry and agentic risk

Overview

The skill mostly does sitemap generation as advertised, but it silently disables HTTPS security checks while crawling websites.

Review before installing. Use only on sites you control or are authorized to crawl, avoid sensitive or internal HTTPS targets until TLS verification is fixed, and check output paths carefully because the tool can write sitemap.xml and robots.txt when requested.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands

Findings (4)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 91% confidence
Finding: The skill documentation clearly instructs use of network access, local file scanning, and file output generation, yet no permissions are declared. That mismatch can prevent proper user review and policy enforcement, making the skill's effective capabilities less transparent and increasing the risk of unexpected data access or writes when invoked.

Context-Inappropriate Capability

Medium

Confidence: 98% confidence
Finding: The crawler explicitly disables both TLS certificate validation and hostname verification before fetching arbitrary URLs. This allows a man-in-the-middle attacker to intercept or modify responses, causing the tool to crawl attacker-controlled content, generate a poisoned sitemap, or leak which targets are being scanned.

Vague Triggers

Medium

Confidence: 82% confidence
Finding: The trigger phrases are broad and overlap with common user intents such as 'robots.txt', 'crawl site', and 'sitemap', which can cause the skill to activate in situations the user did not specifically intend. Because this skill performs network crawling and local file scanning, accidental invocation broadens exposure to unnecessary network requests or filesystem access.

Missing User Warnings

Medium

Confidence: 99% confidence
Finding: Disabling TLS verification without any user warning defeats the trust guarantees of HTTPS for all crawled sites. In this skill's context, the agent may be asked to crawl external domains, so a network attacker can tamper with fetched HTML and injected links, affecting discovery results and any generated sitemap or robots.txt artifacts.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.insecure_tls_verification

HTTPS certificate verification is disabled.

Warn

Code: suspicious.insecure_tls_verification
Location: scripts/sitemap_gen.py:76