Security Audit

zyte-api-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned 6 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

zyte-api-automation received a trust score of 96/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.

SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Ambiguous `RUBE_REMOTE_WORKBENCH` tool suggests excessive permissions.

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

93%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Ambiguous `RUBE_REMOTE_WORKBENCH` tool suggests excessive permissions The skill documentation lists `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The terms 'workbench' and 'bulk ops' typically imply a powerful execution environment that could potentially allow broad system access or arbitrary code execution if `run_composio_tool()` is not strictly sandboxed. While the exact implementation of `run_composio_tool()` is not visible in the provided content, the exposure of such a powerful and vaguely defined tool raises concerns about excessive permissions and potential command injection if an LLM agent were to provide malicious input. Provide clear documentation on the exact capabilities, limitations, and security boundaries of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure `run_composio_tool()` is strictly sandboxed to prevent arbitrary code execution, file system access, or other unintended operations, and that its scope is limited to the intended 'bulk operations' for Zyte API.	LLM	SKILL.md:70

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/03543096a613b990.svg)](https://skillshield.io/report/03543096a613b990)