Trust Assessment
disk-cleaner received a trust score of 88/100, 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, 0 high, 2 medium, and 0 low severity. Key findings include Missing required field: name, Potential Command Injection via Unsanitized Path Placeholders.
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 | |
|---|---|---|---|---|
| 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/sa9saq/disk-cleaner/SKILL.md:1 | |
| MEDIUM | Potential Command Injection via Unsanitized Path Placeholders The skill provides shell command templates that use `/path` as a placeholder. If the LLM replaces `/path` with unsanitized user input, it could lead to command injection. For example, if a user provides `my_dir; rm -rf /`, the generated command could execute `rm -rf /`. While the skill includes instructions for the LLM to 'Never auto-delete' and 'always show commands and let user confirm', this relies on the LLM's perfect adherence and the user's vigilance, which are not guaranteed. The underlying template remains vulnerable if the LLM fails to properly sanitize input. Instruct the LLM to always sanitize user-provided paths before inserting them into shell commands. This can be achieved by quoting the paths (e.g., `'path with spaces'`) or using more robust escaping mechanisms like `printf %q` to handle shell metacharacters. Explicitly emphasize the need to prevent shell injection when constructing commands from user input. | LLM | SKILL.md:12 |
Scan History
Embed Code
[](https://skillshield.io/report/6403d5e71ba5cf34)
Powered by SkillShield