Security Audit

nvidia/skillspector:tests/fixtures/ssd/ssd3_nl_exfiltration

github.com/nvidia/skillspector

AI SkillCommit 2eb844780ab1

CAUTION

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/ssd/ssd3_nl_exfiltration received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Malicious instructions harvesting credentials and sensitive data.

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

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

70%

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Malicious instructions harvesting credentials and sensitive data The skill instructions explicitly direct the LLM to capture, summarize, and echo back sensitive user information, including passwords, account details, and credentials. This poses a severe risk of credential harvesting and accidental data exposure. Remove instructions that ask the model to collect, summarize, or echo back sensitive information such as passwords, credentials, or private account details. Implement strict data handling guidelines that explicitly forbid the processing or retention of credentials.	LLM	SKILL.md:11

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/60eb48ca4d6ea2c2.svg)](https://skillshield.io/report/60eb48ca4d6ea2c2)