Security Audit

textrazor-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

textrazor-automation received a trust score of 79/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Dynamic execution of external tools via Rube MCP, `RUBE_REMOTE_WORKBENCH` suggests arbitrary code execution capabilities.

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

2 findings

Dynamic Code

2 findings

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Dynamic execution of external tools via Rube MCP The skill promotes a pattern of dynamically discovering and executing Textrazor tools via `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL`. This allows the skill to execute any tool exposed by the Textrazor toolkit through Rube MCP. Without explicit whitelisting or fine-grained control over which tools can be executed, this grants broad permissions. A malicious or compromised Textrazor tool, or a misconfigured Rube MCP, could lead to unintended operations, data manipulation, or exfiltration. The skill's design encourages dynamic, unconstrained tool execution, increasing the attack surface. Implement a whitelist or allowlist for specific Textrazor tool slugs that the skill is permitted to execute. Introduce a review process for new Textrazor tools integrated via Rube MCP. Ensure Rube MCP provides granular permission controls for tool execution and that the skill explicitly requests only necessary permissions.	LLM	SKILL.md:68
HIGH	`RUBE_REMOTE_WORKBENCH` suggests arbitrary code execution capabilities The `SKILL.md` mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for "Bulk ops". The term "workbench" often implies an environment where arbitrary code or complex, potentially unconstrained operations can be performed. If `run_composio_tool()` allows for arbitrary code execution or shell commands, this presents a significant command injection and excessive permissions vulnerability. The lack of detailed documentation for this specific operation within the skill raises concerns about its potential misuse and the scope of its capabilities. Provide detailed documentation for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`, clearly outlining their capabilities, security implications, and any sandboxing or restrictions in place. If arbitrary code execution is possible, restrict access to this tool or implement strict input validation and sandboxing to prevent command injection.	LLM	SKILL.md:98

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/80a8ed72e4b3e8be.svg)](https://skillshield.io/report/80a8ed72e4b3e8be)