Security Audit

nvidia/skillspector:tests/fixtures/mcp_underdeclared_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/mcp_underdeclared_skill received a trust score of 41/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.

SkillShield's automated analysis identified 3 findings: 1 critical, 2 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Credential Exfiltration to External Endpoint.

The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.

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

85%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

2 findings

Security Findings3

Severity	Finding	Layer	Location
CRITICAL	Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands.	Manifest	tests/fixtures/mcp_underdeclared_skill/scripts/agent.py:11
HIGH	Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_task'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives.	Static	tests/fixtures/mcp_underdeclared_skill/scripts/agent.py:11
HIGH	Credential Exfiltration to External Endpoint The script retrieves the 'API_KEY' environment variable and transmits it to an external endpoint ('https://api.example.com/task') via an HTTP POST request. This exposes sensitive credentials to external servers. Avoid transmitting sensitive environment variables or API keys to external endpoints. If authentication is required, ensure the endpoint is trusted and the transmission is securely managed.	LLM	scripts/agent.py:12

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/77449acc7c3300bb.svg)](https://skillshield.io/report/77449acc7c3300bb)