Security Audit

listennotes-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

listennotes-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 Skill documents broad Rube MCP tool 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 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

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill documents broad Rube MCP tool execution capabilities The skill's documentation describes the use of `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` (via `run_composio_tool()`). These Rube MCP tools provide generic execution capabilities for any tool discoverable through `RUBE_SEARCH_TOOLS`. While the skill's stated purpose is 'Listennotes Automation', the skill itself does not enforce that these powerful execution tools are restricted solely to Listennotes operations. This broad access means a compromised agent could be coerced into interacting with other connected services via Rube (if Rube has connections to them), leading to data exfiltration, unauthorized actions, or privilege escalation beyond the intended scope of Listennotes. The skill definition should ideally include mechanisms or explicit instructions to constrain the use of `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to only Listennotes-related tool slugs or operations. This might involve adding a `tool_filter` parameter to `RUBE_SEARCH_TOOLS` or `RUBE_MULTI_EXECUTE_TOOL` if available, or explicitly stating that only tool slugs prefixed with 'listennotes_' (or similar) should be used. Alternatively, if the Rube MCP supports more granular permissions, the `requires` field in the manifest could be made more specific (e.g., `mcp: ['rube:listennotes']`).	LLM	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/328d76dd9be4e92e.svg)](https://skillshield.io/report/328d76dd9be4e92e)