Security Audit

turso-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

turso-automation received a trust score of 86/100, 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 Broad database access via Rube MCP tools.

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

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad database access via Rube MCP tools The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to interact with the Turso database. These tools, particularly `RUBE_MULTI_EXECUTE_TOOL` which accepts a `tool_slug` and arbitrary `arguments`, and `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`, imply the ability to execute a wide range of operations exposed by the underlying Turso toolkit. If the Turso toolkit provides broad database manipulation capabilities (e.g., read/write/delete arbitrary data, execute arbitrary SQL queries), this skill effectively grants the LLM excessive permissions to the connected Turso database. This could lead to unauthorized data access, modification, or deletion. Implement fine-grained access control within the Rube MCP or the Turso toolkit itself to restrict the types of operations an LLM can perform. For example, configure the toolkit to allow only read-only access for certain use cases, or restrict operations to specific tables/schemas. Ensure that generic execution functions like `run_composio_tool()` are not used for sensitive operations without strict validation and authorization checks.	LLM	SKILL.md:48

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/00cffa42aec6b940.svg)](https://skillshield.io/report/00cffa42aec6b940)