Security Audit

livesession-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

livesession-automation received a trust score of 85/100, 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, 0 high, 1 medium, and 0 low severity. Key findings include Broad Dynamic Tool Execution 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 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

93%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Broad Dynamic Tool Execution via Rube MCP The skill's manifest requires access to the Rube MCP (`mcp:rube`), and the documentation explicitly encourages dynamic discovery and execution of tools. The agent is instructed to use `RUBE_SEARCH_TOOLS` to find available tools and then execute them via `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH` (which can run `run_composio_tool()`). This design grants the agent broad, dynamic execution capabilities within the Composio ecosystem, allowing it to interact with any 'Livesession operations' or other 'Composio tools' made available through Rube MCP. While intended for flexibility, this level of dynamic access significantly increases the attack surface, as a compromised agent could potentially execute a wide range of unintended or malicious operations. Consider if the agent's access to Rube MCP can be scoped more narrowly, or if specific tools within Rube MCP can be whitelisted/blacklisted. Ensure that the agent's internal logic for selecting and executing dynamically discovered tools is robust against malicious or unintended tool execution. Implement strict input validation for any user-provided data passed to tool arguments.	LLM	SKILL.md:28

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/4d6104c6f7c47cf0.svg)](https://skillshield.io/report/4d6104c6f7c47cf0)