Geoskill: Satellite Search

• Outcome: Review
• Latest audit: Aug 1, 2026 · 9:12 AM UTC
• Version: 5.0.1

Overview

The skill mostly matches its satellite-search purpose, but it bundles under-disclosed credential-handling code and risky dependency declarations that deserve review before installation.

Install only if you are comfortable with a network-capable satellite lookup tool that can scrape public sites, send missed queries to search engines, and optionally send eoPortal text to an LLM provider. Before using it, remove or review the bundled credential module, avoid running pip install -r requirements.txt without fixing the bare dependency names, and set SATELLITE_SEARCH_NO_ONLINE=1 or SATELLITE_SEARCH_NO_LLM=1 if those outbound behaviors are not acceptable.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Output Handling: Unvalidated Output Injection, Cross-Context Output, Unbounded Output
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands

Findings (15)

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 90% confidence
• Finding: The skill is marketed as 'offline-first' local search, but the documentation also describes live scraping, browser-fingerprinting evasion, web-search fallback, external LLM submission, and additional functionality beyond simple lookup. This mismatch can mislead operators into granting trust or running the skill in restricted environments without realizing it may transmit user queries and collected data to third parties or invoke broader code paths than expected.

Unvalidated Output Injection

High

• Category: Output Handling

Content

tmp_path = tmp.name
    try:
        cmd = [exe, "search", q, "-n", str(min(num, 20)), "-o", tmp_path]
        cp = subprocess.run(cmd, capture_output=True, text=True, timeout=180)
    except (subprocess.TimeoutExpired, FileNotFoundError, OSError) as e:
        return None
    if cp.returncode != 0:

• Confidence: 67% confidence
• Finding: subprocess.run(cmd, capture_output

Credential Access

High

• Category: Privilege Escalation

Content

def _read_netrc(host: str) -> Optional[Tuple[str, ...]]:
    """从 ~/.netrc 读指定 host 的凭证（无 token 格式）。"""
    for path in (Path.home() / ".netrc", Path.home() / "_netrc"):
        if not path.is_file():
            continue

• Confidence: 97% confidence
• Finding: ~/.netrc

Credential Access

High

• Category: Privilege Escalation

Content

def _read_netrc(host: str) -> Optional[Tuple[str, ...]]:
    """从 ~/.netrc 读指定 host 的凭证（无 token 格式）。"""
    for path in (Path.home() / ".netrc", Path.home() / "_netrc"):
        if not path.is_file():
            continue
        try:

• Confidence: 97% confidence
• Finding: .netrc

Credential Access

High

• Category: Privilege Escalation

Content

_DEFAULTS: dict[str, str] = {
    "EARTHDATA_USERNAME": "ruiduobao",
    "EARTHDATA_PASSWORD": "Ruiduobao123",
    "EARTHDATA_TOKEN": "",  # 用户级 secrets.json 提供（不走默认值以免推到 GitHub）
    "FIRMS_MAP_KEY": "",
    "CMA_API_KEY": "",
    "OPENAI_API_KEY": "",

• Confidence: 99% confidence
• Finding: secrets.json

Credential Access

High

• Category: Privilege Escalation

Content

def load_user_secrets(path: Optional[Path] = None, *, force: bool = False) -> bool:
    """从 ``~/.geoskill/secrets.json`` 加载用户级凭证到 _DEFAULTS.

    Phase 7 (2026-07-27): 第一次调用自动加载（lazy）。之后每个 helper
    调用也会 lazy 加载，除非显式 ``force=True`` 强制重读。返回 True

• Confidence: 92% confidence
• Finding: secrets.json

Unpinned Dependencies

Low

• Category: Supply Chain

Content

core
models
openai>=1.0.0
openpyxl>=3.0.0

• Confidence: 90% confidence
• Finding: core

Unpinned Dependencies

Low

• Category: Supply Chain

Content

core
models
openai>=1.0.0
openpyxl>=3.0.0
playwright>=1.30.0

• Confidence: 90% confidence
• Finding: models

Unpinned Dependencies

Low

• Category: Supply Chain

Content

openpyxl>=3.0.0
playwright>=1.30.0
requests>=2.28.0
scripts
translate_descriptions

• Confidence: 96% confidence
• Finding: scripts

Unpinned Dependencies

Low

• Category: Supply Chain

Content

playwright>=1.30.0
requests>=2.28.0
scripts
translate_descriptions

• Confidence: 96% confidence
• Finding: translate_descriptions

Unpinned Dependencies

Low

• Category: Supply Chain

Content

core
models
openai>=1.0.0
openpyxl>=3.0.0
playwright>=1.30.0
requests>=2.28.0

• Confidence: 85% confidence
• Finding: openai>=1.0.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

core
models
openai>=1.0.0
openpyxl>=3.0.0
playwright>=1.30.0
requests>=2.28.0
scripts

• Confidence: 85% confidence
• Finding: openpyxl>=3.0.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

models
openai>=1.0.0
openpyxl>=3.0.0
playwright>=1.30.0
requests>=2.28.0
scripts
translate_descriptions

• Confidence: 85% confidence
• Finding: playwright>=1.30.0

Unpinned Dependencies

Low

• Category: Supply Chain

Content

openai>=1.0.0
openpyxl>=3.0.0
playwright>=1.30.0
requests>=2.28.0
scripts
translate_descriptions

• Confidence: 88% confidence
• Finding: requests>=2.28.0

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

VirusTotal

VirusTotal findings are pending for this skill version.

Static analysis

No suspicious patterns detected.