Security Audit
simla-com-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
simla-com-automation 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 Unconstrained Access to Business System Operations.
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 17, 2026 (commit 99e2a295). 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 | Unconstrained Access to Business System Operations The skill describes the use of generic execution tools (`RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`) which allow an LLM to invoke any operation exposed by the underlying Simla Com toolkit. Simla Com is a business application that typically handles sensitive data and critical operations (e.g., customer data management, financial transactions, data deletion). The skill's documentation does not include any mechanisms or recommendations to limit the scope of operations an LLM can perform, nor does it suggest requiring user confirmation for potentially destructive or sensitive actions. This broad, unconstrained access to a business system's full API via generic execution tools poses a significant risk. A malicious or poorly-formed prompt could instruct the LLM to perform unintended, destructive, or data-exfiltrating actions if the connected Simla Com account has the necessary permissions. Implement explicit scope limitations for the Simla Com connection used by the agent, ensuring it only has permissions for necessary operations. Add warnings in the skill documentation about the broad capabilities of the execution tools and recommend requiring explicit user confirmation for sensitive or destructive operations. Consider implementing a 'human-in-the-loop' approval process for high-impact actions. | LLM | SKILL.md:40 |
Scan History
Embed Code
[](https://skillshield.io/report/58cdec3fa55adbdd)
Powered by SkillShield