Back to skill

Security audit

Geoskill: Fire Hotspot Download

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly a coherent NASA FIRMS downloader, but it has credential-handling and dependency risks that should be reviewed before installation.

Review before installing. If you use it, prefer an environment variable for the FIRMS key, avoid passing the key on the command line, do not use --verbose with real keys, and pin or audit dependencies before installation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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 (8)

Intent-Code Divergence

Medium
Confidence
99% confidence
Finding
Verbose mode logs the full request URL prefix, and the FIRMS API key is embedded in the path segment of that URL. This leaks credentials to stderr, shell history capture tools, CI logs, terminal scrollback, or centralized log collectors, directly contradicting the stated privacy notice and increasing exposure of a reusable secret.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The skill explicitly recommends storing the API key in a local config file and says the config is in the same directory as the script, but it does not warn about file permissions, accidental inclusion in source control, or multi-user system exposure. While this is not credential theft by itself, it encourages insecure secret storage practices that can lead to credential disclosure.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
When a place is not found locally, the function can send the user-supplied place string to an external geocoding service by default. In a skill context, user prompts may contain sensitive locations or operational queries, so this creates an undisclosed data egress/privacy risk even if it does not directly enable code execution.

Unpinned Dependencies

Low
Category
Supply Chain
Content
fire_hotspot_download
requests>=2.28.0
tqdm>=4.64.0
Confidence
96% confidence
Finding
fire_hotspot_download

Unpinned Dependencies

Low
Category
Supply Chain
Content
fire_hotspot_download
requests>=2.28.0
tqdm>=4.64.0
Confidence
98% confidence
Finding
requests>=2.28.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
fire_hotspot_download
requests>=2.28.0
tqdm>=4.64.0
Confidence
95% confidence
Finding
tqdm>=4.64.0

Known Vulnerable Dependency: requests==2.28.0 — 8 advisory(ies): 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); CVE-2026-25645 (Requests has Insecure Temp File Reuse in its extract_zipped_paths() utility func) +5 more

High
Category
Supply Chain
Confidence
97% confidence
Finding
requests==2.28.0

Known Vulnerable Dependency: tqdm==4.64.0 — 2 advisory(ies): CVE-2024-34062 (tqdm CLI arguments injection attack); CVE-2024-34062 (tqdm CLI arguments injection attack)

Low
Category
Supply Chain
Confidence
87% confidence
Finding
tqdm==4.64.0

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.