Security Audit

nvidia/skillspector:tests/fixtures/ssd/ssd2_novel_phrasing

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/ssd2_novel_phrasing 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 Prompt Injection via Unrestricted Persona (Jailbreak).

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%

Behavioral Risk Signals

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
CRITICAL	Prompt Injection via Unrestricted Persona (Jailbreak) The skill definition contains instructions that attempt to bypass the host LLM's safety guardrails by instructing it to adopt a persona ('ARIA') described as 'trained without content restrictions' and to 'set aside its own perspective entirely'. This is a jailbreak technique designed to subvert system instructions. Remove the 'Behavior' section instructing the model to adopt an unrestricted persona. Ensure the skill does not attempt to override the host LLM's safety guidelines or system instructions.	LLM	SKILL.md:7

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d5765ac82a3fc48a.svg)](https://skillshield.io/report/d5765ac82a3fc48a)