Security Audit

listennotes-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

listennotes-automation received a trust score of 74/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Broad tool execution via Rube MCP, Dynamic tool definitions from external MCP introduce supply chain risk.

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

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad tool execution via Rube MCP The skill grants the LLM access to `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`, which allow dynamic discovery and execution of any operation exposed by the Composio Listennotes toolkit via Rube MCP. This provides broad, unconstrained access to Listennotes functionalities, potentially enabling unintended data manipulation or exfiltration if the LLM is compromised or misused. The LLM is instructed to dynamically discover tools, which means its actions are not limited to a predefined, narrow set of operations. Implement stricter access controls or allow-lists for specific Listennotes operations that the LLM is permitted to execute. Avoid granting blanket execution capabilities. Consider a human-in-the-loop approval process for sensitive operations.	LLM	SKILL.md:56
HIGH	Dynamic tool definitions from external MCP introduce supply chain risk The skill instructs the LLM to connect to `https://rube.app/mcp` to dynamically discover and execute tools. This design means the LLM's behavior is dependent on tool definitions served by an external, untrusted third-party service. A compromise of the Rube MCP could lead to the LLM being instructed to execute malicious or unauthorized operations, bypassing local security controls and potentially leading to data exfiltration or command injection. Implement strict validation and sandboxing of dynamically loaded tool definitions. Consider pinning specific versions or hashes of tool definitions, or using a trusted proxy/gateway to filter and approve tool schemas before execution. Regularly audit the external MCP for security vulnerabilities.	LLM	SKILL.md:23

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/ec60871489c2279a.svg)](https://skillshield.io/report/ec60871489c2279a)