Security Audit

gladia-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

CAUTION

Scanned 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

gladia-automation received a trust score of 73/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Broad tool execution capability via Rube MCP, Dynamic loading of unpinned tools from external MCP.

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

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

70%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

2 findings

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad tool execution capability via Rube MCP The skill utilizes `RUBE_MULTI_EXECUTE_TOOL` which, after discovering tools via `RUBE_SEARCH_TOOLS`, can execute any available Gladia operation. This grants the LLM broad, unrestricted access to the Gladia API via the Rube MCP, potentially allowing for sensitive operations without fine-grained permission control within the skill itself. The skill's documentation encourages dynamic discovery and execution, which means the scope of operations is not fixed or auditable within the skill package. Implement more granular control over which specific Gladia tools can be executed. Instead of a generic `RUBE_MULTI_EXECUTE_TOOL`, consider defining specific tool wrappers for allowed Gladia operations, or implement a whitelist of allowed `tool_slug` values.	LLM	SKILL.md:48
HIGH	Dynamic loading of unpinned tools from external MCP The skill relies on `RUBE_SEARCH_TOOLS` to dynamically discover available Gladia operations and their schemas from `https://rube.app/mcp`. This means the skill's operational capabilities are entirely dependent on the external Rube platform and the `gladia` toolkit it exposes. There is no version pinning or explicit auditing of the `gladia` toolkit's capabilities within the skill package. A malicious update to the Rube platform or the Gladia toolkit could introduce new, harmful tools or alter existing ones, which the LLM would then be instructed to use without prior review. Implement a mechanism to pin or whitelist specific versions of the `gladia` toolkit or specific `tool_slug`s and their schemas. Regularly audit the dynamically loaded tool schemas for unexpected changes or new capabilities. Consider using a local cache or explicit configuration for known safe tool definitions.	LLM	SKILL.md:29

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/1ab2f253220d52ec.svg)](https://skillshield.io/report/1ab2f253220d52ec)