Security Audit

gagelist-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

gagelist-automation received a trust score of 84/100, 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, 0 medium, and 1 low severity. Key findings include Skill enables execution of arbitrary Rube/Composio tools, Unpinned Rube MCP dependency in manifest.

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

83%

Behavioral Risk Signals

Network Access

2 findings

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Skill enables execution of arbitrary Rube/Composio tools The skill's documentation instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to execute dynamically discovered tools from the `gagelist` toolkit via Rube MCP. This design grants the LLM broad and undefined capabilities, as the specific actions performed depend entirely on the external Rube MCP and the `gagelist` toolkit's offerings, which can change. This allows the LLM to perform any action exposed by the `gagelist` toolkit, potentially including sensitive operations, without explicit limitations within the skill's definition. Implement stricter controls or a whitelist for allowed `tool_slug` values or `run_composio_tool()` arguments. Ensure the Rube MCP and `gagelist` toolkit enforce least privilege and provide granular permissions. The skill itself could be designed to only call specific, pre-approved tool slugs rather than any discovered tool.	LLM	SKILL.md:49
LOW	Unpinned Rube MCP dependency in manifest The `requires` field in the manifest specifies `{"mcp": ["rube"]}` without a version or specific endpoint. While the documentation suggests `https://rube.app/mcp`, the manifest itself does not enforce this. This lack of pinning could allow a client to configure a different or malicious "rube" MCP, leading to unexpected behavior or security vulnerabilities if the client's configuration is compromised or misconfigured. Update the manifest to include a specific version or a trusted endpoint for the "rube" MCP, if supported by the ecosystem, to ensure consistency and prevent substitution.	LLM	SKILL.md:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/30ce9e529dccc373.svg)](https://skillshield.io/report/30ce9e529dccc373)