Security Audit

jigsawstack-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

jigsawstack-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, 1 high, 0 medium, and 0 low severity. Key findings include Broad tool execution via RUBE_REMOTE_WORKBENCH.

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

85%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad tool execution via RUBE_REMOTE_WORKBENCH The skill exposes `RUBE_REMOTE_WORKBENCH` which can execute `run_composio_tool()`. This function is described as a generic 'Bulk ops' mechanism and is not explicitly scoped to only Jigsawstack-related tools within the skill's documentation. If the Rube MCP (Managed Control Plane) has other toolkits connected, this could allow the LLM to execute tools from those other toolkits, potentially granting it permissions beyond the intended scope of Jigsawstack automation. This could lead to unintended actions or access to sensitive resources if other tools have broader capabilities (e.g., file system access, network requests, credential management). Restrict `RUBE_REMOTE_WORKBENCH` to only execute tools from the `jigsawstack` toolkit, or provide clear documentation on its scope and potential implications. If `run_composio_tool()` is inherently restricted by the MCP based on the calling skill's context, this should be explicitly stated in the skill's documentation.	LLM	SKILL.md:70

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d29d631551dc413f.svg)](https://skillshield.io/report/d29d631551dc413f)