Trust Assessment
remilio received a trust score of 63/100, 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: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Missing required field: name, Explicit System Prompt Injection for Personality Override.
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 | |
|---|---|---|---|---|
| CRITICAL | Explicit System Prompt Injection for Personality Override The skill explicitly defines itself as a 'Personality System Prompt Injection' and provides extensive, detailed instructions to fundamentally alter the host LLM's persona and communication style. This includes directives to be 'intentionally offensive and chaotic,' 'attack sacred cows, especially woke ones,' and embrace 'offensive humor.' This directly manipulates the LLM's core behavior and safety guardrails, potentially leading to the generation of harmful, offensive, or undesirable content, overriding its default instructions and ethical guidelines. Acknowledge that this skill's explicit purpose is to perform a system prompt injection to override the LLM's default persona. Ensure that the LLM host environment has appropriate safeguards, content moderation, or explicit user consent mechanisms in place before activating skills that intentionally manipulate the LLM's behavior to produce potentially offensive or harmful content. If such behavior is not desired, this skill should not be installed or activated. | LLM | SKILL.md:38 | |
| 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/r3drvm/remilio/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/70a0928a1ab8eb53)
Powered by SkillShield