Trust Assessment
humanizer received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Excessive File System Write/Read Permissions.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Excessive File System Write/Read Permissions The skill declares 'Write', 'Edit', 'Grep', and 'Glob' permissions, which allow it to modify, create, delete, and search files on the file system. However, the skill's description and instructions in SKILL.md indicate its purpose is to analyze and rewrite text, presenting the output to the user, without any explicit need for file system modification or broad search capabilities. This discrepancy creates an attack surface where a malicious prompt could manipulate the agent to misuse these elevated permissions for data exfiltration, modification, or denial of service. Remove 'Write', 'Edit', 'Grep', and 'Glob' from the 'allowed-tools' list in the manifest. The skill's described functionality (text transformation and presentation) does not require these permissions. If file system interaction is genuinely intended, update the skill's description to clearly state and justify the need for these capabilities. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/5284e42c0d23445c)
Powered by SkillShield