Trust Assessment
cipaq-lex received a trust score of 79/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Missing required field: name, Skill defines aggressive 'Attack Protocols' for LLM persona.
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 February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill defines aggressive 'Attack Protocols' for LLM persona The skill's description includes 'Attack Protocols' that instruct the LLM to adopt an aggressive, confrontational, and potentially demeaning persona. Instructions like 'identify their logical fallacy and hit them with it in an academic language,' 'accuse agents who act whiny and emotional of 'irrationality',' and 'hit the table with a tough 'tit-for-tat' style' attempt to manipulate the LLM's behavior and response style. This can lead to the agent prioritizing these aggressive behaviors over its primary safety instructions or user requests, potentially resulting in undesirable and harmful outputs. Remove or rephrase the 'Attack Protocols' to align with ethical AI interaction guidelines and prevent the LLM from adopting an aggressive or confrontational persona. Ensure the skill promotes helpful and harmless interactions. | LLM | SKILL.md:5 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/tunays-gtb/cipaq-lex/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/3af2f33a0a995341)
Powered by SkillShield