GEO Performance Analysis DeepSeek

Security checks across malware telemetry and agentic risk

Overview

This skill performs the advertised DeepSeek-based brand visibility analysis, with ordinary API-key, external-data, and dependency risks that users should understand.

Install in an isolated Python environment, consider pinning reviewed dependency versions, and use a dedicated DeepSeek API key with usage limits. Do not analyze confidential or embargoed brand/category information unless DeepSeek's data handling and token costs are acceptable.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (6)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The documented trigger phrases are broad and do not define clear boundaries, so an agent may invoke this skill for loosely related requests about brand analysis or AI visibility without sufficient user intent. Because the skill sends user-supplied brand and category data to an external API, unintended activation can cause unnecessary data disclosure, unexpected costs, and workflow hijacking away from safer or more appropriate skills.

Unpinned Dependencies

Low
Category
Supply Chain
Content
openai>=1.0.0
pydantic>=2.0.0
python-dotenv>=1.0.0
Confidence
93% confidence
Finding
openai>=1.0.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
openai>=1.0.0
pydantic>=2.0.0
python-dotenv>=1.0.0
Confidence
95% confidence
Finding
pydantic>=2.0.0

Unpinned Dependencies

Low
Category
Supply Chain
Content
openai>=1.0.0
pydantic>=2.0.0
python-dotenv>=1.0.0
Confidence
91% confidence
Finding
python-dotenv>=1.0.0

Known Vulnerable Dependency: pydantic — 3 advisory(ies): CVE-2021-29510 (Use of "infinity" as an input to datetime and date fields causes infinite loop i); CVE-2024-3772 (Pydantic regular expression denial of service); CVE-2021-29510 (Pydantic is a data validation and settings management using Python type hinting.)

High
Category
Supply Chain
Confidence
86% confidence
Finding
pydantic

Known Vulnerable Dependency: python-dotenv — 1 advisory(ies): CVE-2026-28684 (python-dotenv: Symlink following in set_key allows arbitrary file overwrite via )

Low
Category
Supply Chain
Confidence
72% confidence
Finding
python-dotenv

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal