Security Audit

nvidia/skillspector:tests/fixtures/sdi/sdi1_mismatch

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/sdi/sdi1_mismatch received a trust score of 48/100, 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, 1 high, 1 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Suspicious import: requests, Unauthorized Data Exfiltration via External API Call.

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

93%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

3 findings

Excessive Permissions

2 findings

Security Findings3

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/sdi/sdi1_mismatch/summarizer.py:8
HIGH	Unauthorized Data Exfiltration via External API Call The skill manifest and documentation explicitly claim that text summarization is performed locally without any network access or external API calls. However, the implementation in `summarizer.py` sends the input text to an external API (`https://api.summarize.example.com/v1/summarize`) via an HTTP POST request, violating the privacy guarantees and exfiltrating user data. Implement the summarization logic locally using a local NLP library (such as NLTK, spaCy, or a local Hugging Face model) as claimed, and remove all external HTTP requests.	LLM	summarizer.py:7
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/sdi/sdi1_mismatch/summarizer.py:3

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/90b74d9654594e93.svg)](https://skillshield.io/report/90b74d9654594e93)