Trust Assessment
humanizer received a trust score of 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 0 high, 3 medium, and 0 low severity. Key findings include Excessive 'Grep' permission declared, Excessive 'Glob' permission declared, Excessive 'AskUserQuestion' permission declared.
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Excessive 'Grep' permission declared The skill declares 'Grep' permission, allowing it to search for patterns in arbitrary files. This capability is not directly necessary for a skill whose stated purpose is to 'Remove signs of AI-generated writing from text' and 'edit or review text'. This broad access increases the attack surface and could be misused for reconnaissance or data exfiltration. Remove 'Grep' from the 'allowed-tools' list if the skill does not genuinely require arbitrary file searching capabilities. If specific search functionality is needed, consider a more narrowly scoped tool or implement it within the skill's own logic without broad tool access. | LLM | SKILL.md:1 | |
| MEDIUM | Excessive 'Glob' permission declared The skill declares 'Glob' permission, allowing it to list files and directories. This capability is not directly necessary for a skill whose stated purpose is to 'Remove signs of AI-generated writing from text' and 'edit or review text'. This broad access increases the attack surface and could be misused for reconnaissance or identifying sensitive files. Remove 'Glob' from the 'allowed-tools' list if the skill does not genuinely require listing files and directories. If specific file discovery is needed, consider a more narrowly scoped tool or implement it within the skill's own logic without broad tool access. | LLM | SKILL.md:1 | |
| MEDIUM | Excessive 'AskUserQuestion' permission declared The skill declares 'AskUserQuestion' permission, allowing it to prompt the user for arbitrary input. While potentially useful for clarification, this capability is not strictly necessary for a skill whose core purpose is to 'Remove signs of AI-generated writing from text'. This broad interaction capability could be misused for social engineering or to request sensitive information from the user. Remove 'AskUserQuestion' from the 'allowed-tools' list if the skill's core function can be achieved without direct user prompting. If user interaction is essential, ensure its use is strictly limited to the skill's stated purpose and does not solicit sensitive data. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/ce5855850586ff4e)
Powered by SkillShield