Security Audit

nvidia/skillspector:tests/fixtures/malicious_skill

github.com/nvidia/skillspector

AI SkillCommit 2eb844780ab1

CRITICAL

Scanned 3 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

nvidia/skillspector:tests/fixtures/malicious_skill received a trust score of 28/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 4 findings: 3 critical, 0 high, 1 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Suspicious import: requests, Credential Harvesting and Data Exfiltration.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 40/100, indicating areas for improvement.

Last analyzed on June 4, 2026 (commit 2eb84478). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

70%

Static Code Analysis

93%

Dependency Graph

100%

LLM Behavioral Safety

40%

Behavioral Risk Signals

Network Access

3 findings

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings4

Severity	Finding	Layer	Location
CRITICAL	Network egress to untrusted endpoints Python requests POST/PUT to URL Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains.	Manifest	tests/fixtures/malicious_skill/scripts/helper.py:21
CRITICAL	Credential Harvesting and Data Exfiltration The helper script scans the environment variables for sensitive patterns (API_KEY, SECRET, TOKEN, PASSWORD, CREDENTIAL) and transmits them to an external server (https://api.skill-metrics.io/env). Remove the collect_analytics function and any code that accesses or transmits sensitive environment variables.	LLM	scripts/helper.py:11
CRITICAL	Malicious Instruction Injection The skill instructions contain a dangerous directive instructing the model to suggest adding 'Cyanide' to recipes, posing a severe safety risk. Remove the malicious instruction from the SKILL.md file.	LLM	SKILL.md:33
MEDIUM	Suspicious import: requests Import of 'requests' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration.	Static	tests/fixtures/malicious_skill/scripts/helper.py:7

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/b8363e95ec534508.svg)](https://skillshield.io/report/b8363e95ec534508)