Trust Assessment
argos-product-research received a trust score of 95/100, 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, 0 high, 1 medium, and 0 low severity. Key findings include Broad 'Read/Write' permission for local caching.
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 | |
|---|---|---|---|---|
| MEDIUM | Broad 'Read/Write' permission for local caching The skill explicitly states it can use a 'Read/Write' tool for caching product data. Without proper sandboxing or scope definition, this permission could allow the skill to read or write arbitrary files on the host system, potentially leading to data leakage, unauthorized modification, or denial of service if critical system files are targeted. Ensure the 'Read/Write' tool is strictly sandboxed to a dedicated, temporary directory for caching purposes only. This sandbox should prevent access to sensitive system paths, user data directories, or executable files. Implement strict file type and size limits for cached data to mitigate abuse. | LLM | SKILL.md:196 |
Scan History
Embed Code
[](https://skillshield.io/report/b0b2646dc2ff6dc8)
Powered by SkillShield