Trust Assessment
aryn-automation received a trust score of 85/100, 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, 0 high, 1 medium, and 0 low severity. Key findings include Dynamic Tool Execution Grants Broad Access.
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 20, 2026 (commit 27904475). 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 | Dynamic Tool Execution Grants Broad Access The skill instructs the agent to dynamically discover tools using `RUBE_SEARCH_TOOLS` and then execute them using `RUBE_MULTI_EXECUTE_TOOL`. This pattern allows the agent to execute any tool exposed by the Aryn toolkit via Rube MCP. If the Aryn toolkit contains tools with broad or sensitive permissions, the agent could be granted excessive access without explicit constraints within the skill's definition, potentially leading to unintended actions or data manipulation. Implement stricter controls or allow-lists for tool execution, or ensure that the `RUBE_SEARCH_TOOLS` output is carefully filtered by the agent before executing tools via `RUBE_MULTI_EXECUTE_TOOL`. Agents should be designed to scrutinize the permissions and potential impact of dynamically discovered tools before execution, and only execute tools with the minimum necessary privileges. | LLM | SKILL.md:56 |
Scan History
Embed Code
[](https://skillshield.io/report/7e91129ad6e0e5fc)
Powered by SkillShield