Security Audit

onepage-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

onepage-automation received a trust score of 93/100, 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 Skill grants broad access to external toolkit operations.

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

93%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Skill grants broad access to external toolkit operations The skill instructs the LLM to dynamically discover and execute tools from the 'onepage' toolkit via Rube MCP. Specifically, it advises using `RUBE_SEARCH_TOOLS` to find available tools and then `RUBE_MULTI_EXECUTE_TOOL` to execute them. This design grants the LLM broad, unrestricted access to all operations exposed by the 'onepage' toolkit. If the 'onepage' toolkit contains sensitive, destructive, or data-accessing operations, an LLM could potentially misuse these capabilities, leading to unintended data modification, deletion, or exposure if compromised or misdirected. Consider implementing more granular control over which specific 'onepage' tools the LLM is permitted to use, perhaps through explicit whitelisting or blacklisting within the skill's instructions or the Rube MCP configuration. Alternatively, ensure that the 'onepage' toolkit itself has robust authorization, confirmation, and auditing mechanisms for sensitive operations.	Static	SKILL.md:39

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/5059e0c71a9aaeeb.svg)](https://skillshield.io/report/5059e0c71a9aaeeb)