Security Audit

smartrecruiters-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

smartrecruiters-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, 0 high, 1 medium, and 0 low severity. Key findings include Exposure of Broad Automation Capabilities 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

93%

Behavioral Risk Signals

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Exposure of Broad Automation Capabilities via RUBE_REMOTE_WORKBENCH The skill documentation exposes the `RUBE_REMOTE_WORKBENCH` tool, specifically mentioning its use for "Bulk ops" with `run_composio_tool()`. This indicates that the LLM, when using this skill, has access to a highly privileged interface capable of performing complex and potentially large-scale operations on Smartrecruiters. While the skill itself doesn't define the exact scope of `run_composio_tool()`, its "bulk ops" nature suggests a significant potential for unauthorized data manipulation, exfiltration, or service disruption if the LLM's execution context is compromised. Implement granular access controls and strict validation within the Rube MCP system for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that any "bulk operations" require explicit user confirmation or are limited to predefined, safe workflows. The skill documentation should also clarify the precise scope and potential impact of this tool.	LLM	SKILL.md:60

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/a281cb8277e057a1.svg)](https://skillshield.io/report/a281cb8277e057a1)