Trust Assessment
file-organizer received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Skill describes broad filesystem access.
The analysis covered 4 layers: dependency_graph, manifest_analysis, llm_behavioral_safety, static_code_analysis. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 11, 2026 (commit 6195a031). 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 | Skill describes broad filesystem access The skill, as described in this rubric, intends to operate across a significant portion of the user's filesystem, including the entire home directory (`~`), `Downloads`, `Documents`, `Projects`, and `Desktop`. This implies that any AI agent implementing this skill would require extensive read, write, move, and delete permissions across these critical user directories. While the rubric emphasizes user confirmation before making changes, the inherently broad scope of operations presents a high-risk surface area if not implemented with robust sandboxing, strict input validation, and granular user interaction for every sensitive action. Any agent implementing this skill must employ strict sandboxing for all file operations. All file modifications (moves, renames, deletions) should require explicit, granular user confirmation for each action or group of actions. The scope of operations should be limited to specific, user-approved directories rather than broad system access, and user input for directory paths must be thoroughly sanitized to prevent command injection. | Unknown | SKILL.md:39 |
Scan History
Embed Code
[](https://skillshield.io/report/c032ee8f456a0178)
Powered by SkillShield