Trust Assessment
invoice-organizer 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 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via Unsanitized Filenames.
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 | Potential Command Injection via Unsanitized Filenames The skill instructs the agent to extract data (Vendor, Description) from untrusted invoice files and use this data to construct filenames and directory paths for shell commands (`mkdir`, `cp`, `mv`). Although "Remove special characters except hyphens" is listed as a "Filename Best Practice," there is no explicit instruction or mechanism described to ensure robust sanitization of these extracted strings before they are incorporated into shell commands. An invoice with a specially crafted vendor name or description (e.g., containing shell metacharacters like `;`, `&`, `|`, `"`, `$`) could lead to command injection, allowing arbitrary commands to be executed on the host system when the agent attempts to create or move files. Implement strict sanitization and escaping of all untrusted data (e.g., vendor names, descriptions) extracted from invoice files before using them in shell commands or file paths. Explicitly instruct the agent to perform this sanitization as a mandatory security requirement, not just a best practice. For example, use a robust library function for path sanitization or ensure all special shell characters are escaped (e.g., by quoting arguments or using a dedicated shell escaping utility). | Unknown | SKILL.md:105 |
Scan History
Embed Code
[](https://skillshield.io/report/e84cf05e0decef70)
Powered by SkillShield