Security Audit

castingwords-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

castingwords-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 Skill instructs LLM to use powerful 'RUBE_REMOTE_WORKBENCH' for bulk 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

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill instructs LLM to use powerful 'RUBE_REMOTE_WORKBENCH' for bulk operations The `SKILL.md` explicitly instructs the LLM to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'workbench' and the generic `run_composio_tool()` suggest a powerful execution environment that could allow for arbitrary code execution, file system access, or network requests if the underlying Composio tools are not properly sandboxed or restricted. This exposes the agent to potential command injection and data exfiltration risks through an overly broad tool, as the skill provides no specific restrictions or safety guidelines for its use. Clarify and restrict the capabilities of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it allows arbitrary Composio tool execution, ensure Composio tools are sandboxed and their permissions are strictly defined and limited. Provide specific examples of safe `run_composio_tool()` usage and explicitly warn against or disallow dangerous operations. If possible, avoid exposing such a broad 'workbench' tool to the LLM without strict guardrails.	LLM	SKILL.md:60

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/cfea984f669de50a.svg)](https://skillshield.io/report/cfea984f669de50a)