Security Audit

wit-ai-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

wit-ai-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 Skill grants broad tool execution capabilities via Rube 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 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

Network Access

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill grants broad tool execution capabilities via Rube MCP The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and mentions `RUBE_REMOTE_WORKBENCH` for 'Bulk ops'. `RUBE_MULTI_EXECUTE_TOOL` allows the execution of any tool discovered via `RUBE_SEARCH_TOOLS`, whose specific capabilities and potential side effects are not constrained or detailed within this skill's definition. Similarly, `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` suggests a generic execution environment. This design grants the LLM broad and potentially unconstrained access to underlying system functionalities or external services, depending on the connected Rube toolkits and their configurations. The skill itself does not define or limit the scope of these tools, effectively inheriting the full permissions of the Rube MCP system. Implement stricter access controls or scope limitations within the Rube MCP configuration or the skill's definition to restrict the types of tools or operations that can be executed via `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. Ensure that the `TOOL_SLUG_FROM_SEARCH` is constrained to only safe and intended Wit AI operations, and that `RUBE_REMOTE_WORKBENCH` operations are similarly sandboxed or limited in scope.	LLM	SKILL.md:40

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/0c3745c3fcd6240c.svg)](https://skillshield.io/report/0c3745c3fcd6240c)