Security Audit

yousearch-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

yousearch-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 Dynamic Tool Discovery and Execution Grants 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 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

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Dynamic Tool Discovery and Execution Grants Excessive Permissions The skill instructs the agent to dynamically discover available tools via `RUBE_SEARCH_TOOLS` (lines 29, 38) and subsequently execute them using `RUBE_MULTI_EXECUTE_TOOL` (line 49). Additionally, `RUBE_REMOTE_WORKBENCH` is mentioned for 'Bulk ops' (line 72). This design pattern grants the agent broad, dynamic execution capabilities, allowing it to potentially access and execute any tool registered with the Rube MCP, not just those explicitly related to Yousearch. This could lead to unintended actions or privilege escalation if the agent's reasoning is compromised or if malicious tools are available through the MCP. Implement stricter access controls on the Rube MCP to limit what tools an agent can discover and execute. Restrict the scope of `RUBE_SEARCH_TOOLS` to specific toolkits or use cases. Ensure that `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` are used with explicit, narrow permissions, and that any remote execution environment is properly sandboxed and monitored.	LLM	SKILL.md:29

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e306ba81b6d5525d.svg)](https://skillshield.io/report/e306ba81b6d5525d)