Security Audit

repairshopr-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

repairshopr-automation received a trust score of 83/100, 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, 1 high, 1 medium, and 0 low severity. Key findings include Potential Command Injection via RUBE_REMOTE_WORKBENCH, Dynamic Tool Discovery Grants Broad API Access.

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

78%

Behavioral Risk Signals

Shell Execution

2 findings

Dynamic Code

2 findings

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via RUBE_REMOTE_WORKBENCH The skill instructs the LLM to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'workbench' and the nature of 'bulk operations' suggest that this tool might allow for arbitrary code execution or highly flexible scripting. If the underlying Rube/Composio system does not strictly validate and sandbox inputs to `run_composio_tool()`, it could be exploited for command injection, granting the LLM excessive permissions to perform unconstrained operations. Clarify the exact capabilities and security boundaries of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that `run_composio_tool()` strictly validates inputs and operates within a secure, sandboxed environment, preventing arbitrary code execution or unintended system access. If it allows scripting, specify the language and available APIs, and ensure strict input sanitization.	LLM	SKILL.md:69
MEDIUM	Dynamic Tool Discovery Grants Broad API Access The skill instructs the LLM to use `RUBE_SEARCH_TOOLS` to dynamically discover available Repairshopr operations and their schemas. This mechanism, followed by execution via `RUBE_MULTI_EXECUTE_TOOL`, grants the LLM broad, dynamic access to the entire Repairshopr API surface exposed by Composio. While intended for automation, this wide scope means that if the LLM's reasoning is compromised (e.g., by a sophisticated prompt injection), it could be instructed to discover and execute any available Repairshopr operation, potentially leading to unintended data modification, deletion, or exfiltration. The skill itself does not define or limit the specific set of tools the LLM is allowed to access. Implement stricter access controls or allow-lists for the tools that the LLM is permitted to discover and execute. Provide mechanisms for administrators to define the exact scope of Repairshopr operations an LLM can perform. Ensure robust input validation and user confirmation for sensitive operations, especially when dynamically discovered tools are involved.	LLM	SKILL.md:42

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/4a07572a40f5bc1c.svg)](https://skillshield.io/report/4a07572a40f5bc1c)