Security Audit

desktime-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

desktime-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 capabilities via Rube MCP.

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

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad tool execution capabilities via Rube MCP The skill exposes powerful tools like `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`. These tools allow the LLM to execute arbitrary Desktime operations and potentially any other Composio tool accessible via the Rube MCP. While this is the intended functionality for automation, it grants very broad permissions to the LLM. If an attacker can manipulate the LLM's prompts, they could leverage these tools to perform unauthorized or destructive actions across various connected services, bypassing granular access controls that might otherwise be in place. The skill itself does not define or enforce granular permissions, relying entirely on the Rube MCP for mediation. Implement strict access controls and input validation within the Rube MCP and the underlying Composio tools. Ensure the LLM's prompts are carefully engineered and monitored to prevent malicious use of these powerful tools. Consider adding more granular permission checks at the skill invocation level or within the Rube MCP configuration to limit the scope of operations an LLM can perform, especially for `RUBE_REMOTE_WORKBENCH`.	LLM	SKILL.md:60

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/efb4da589518766c.svg)](https://skillshield.io/report/efb4da589518766c)