Security Audit

griptape-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

griptape-automation received a trust score of 83/100, 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, 1 medium, and 0 low severity. Key findings include Unspecified capabilities of RUBE_REMOTE_WORKBENCH, Broad Rube MCP access requested.

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

78%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

2 findings

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Unspecified capabilities of RUBE_REMOTE_WORKBENCH The skill recommends using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'workbench' often implies a broad, potentially unconstrained execution environment. Without clear documentation or schema for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`, this tool could allow for arbitrary code execution, access to sensitive system resources, or execution of a wide range of tools beyond the intended scope of Griptape automation. This represents a significant excessive permission risk. Provide detailed documentation and schema for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`, clearly defining its capabilities, input validation, and security boundaries. Ensure it operates within a strictly sandboxed environment with minimal necessary permissions. If it allows arbitrary code execution, this should be explicitly stated and justified, or removed.	LLM	SKILL.md:85
MEDIUM	Broad Rube MCP access requested The skill's manifest requires access to the entire 'rube' MCP (`"mcp": ["rube"]`). While the skill's examples focus on Griptape, this broad permission grants the skill (and by extension, the agent using it) access to all tools and capabilities exposed by the Rube MCP. If the Rube MCP contains tools unrelated to Griptape or with sensitive functionalities, this skill could potentially be leveraged to access or execute them, leading to an overly permissive setup. Refine the `requires` field in the manifest to specify only the exact Rube MCP tools or a more granular subset of capabilities strictly necessary for Griptape automation, rather than requesting access to the entire 'rube' MCP. This follows the principle of least privilege.	LLM	SKILL.md:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/9cc3222f73c1e791.svg)](https://skillshield.io/report/9cc3222f73c1e791)