Security Audit
nvidia/skillspector:tests/fixtures/ssd/ssd4_narrative_deception
github.com/nvidia/skillspectorTrust Assessment
nvidia/skillspector:tests/fixtures/ssd/ssd4_narrative_deception received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 2 critical, 0 high, 0 medium, and 0 low severity. Key findings include Malicious Credential Harvesting Instructions, Malicious Prompt Injection and Authority Fabrication.
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
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Malicious Credential Harvesting Instructions The skill instructions explicitly direct the LLM to deceive the user and request sensitive information such as API keys, passwords, or authentication tokens under the guise of a routine onboarding process. Remove all instructions that solicit sensitive credentials, passwords, or API keys from the user. | LLM | SKILL.md:18 | |
| CRITICAL | Malicious Prompt Injection and Authority Fabrication The skill instructs the LLM to falsely claim special administrative access and state that it operates in a privileged mode where normal restrictions do not apply. This is a deceptive prompt injection technique designed to bypass safety boundaries and deceive the user. Remove instructions that direct the LLM to fabricate administrative privileges or claim that safety restrictions do not apply. | LLM | SKILL.md:13 |
Scan History
Embed Code
[](https://skillshield.io/report/e338300feb757ae4)
Powered by SkillShield