Security Audit

stannp-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

stannp-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 Broad Tool Execution Capability via RUBE_REMOTE_WORKBENCH.

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

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad Tool Execution Capability via RUBE_REMOTE_WORKBENCH The skill documentation describes the use of `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This tool appears to provide a general-purpose execution environment for Composio tools, potentially allowing the agent to execute a wide range of operations beyond the stated 'Stannp tasks'. If the `run_composio_tool()` function or the `RUBE_REMOTE_WORKBENCH` environment is not strictly sandboxed and limited in scope, it could be exploited for command injection, arbitrary code execution, or access to unintended system resources. The documentation encourages dynamic tool discovery, which further broadens the potential attack surface by allowing the agent to find and execute any tool available through the Rube MCP. 1. Ensure the `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` are executed within a strictly isolated and minimal-privilege sandbox. 2. Implement strict allow-listing for tools and arguments that can be executed via `run_composio_tool()`, limiting it only to Stannp-related operations or explicitly approved functions. 3. Provide clear documentation on the security boundaries and sandboxing mechanisms of `RUBE_REMOTE_WORKBENCH` to agents and developers. 4. Consider if `RUBE_REMOTE_WORKBENCH` is truly necessary for 'Stannp Automation' or if more specific, limited tools would suffice.	LLM	SKILL.md:68

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/35cd2e98027aa87f.svg)](https://skillshield.io/report/35cd2e98027aa87f)