Security Audit

dungeon-fighter-online-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

dungeon-fighter-online-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 Broad access to Dungeon Fighter Online 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 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	Broad access to Dungeon Fighter Online operations The skill instructs the LLM to use `RUBE_SEARCH_TOOLS` to discover available Dungeon Fighter Online operations and then `RUBE_MULTI_EXECUTE_TOOL` to execute any of these discovered tools. This grants the LLM broad, unrestricted access to all functionalities exposed by the Dungeon Fighter Online toolkit. While this is the intended purpose for automation, it presents a risk if the LLM is compromised or misdirected, as it could perform sensitive or unintended actions within the user's Dungeon Fighter Online account without specific constraints. Consider implementing stricter access controls or fine-grained permissions within the Rube MCP for the Dungeon Fighter Online toolkit, if available. Alternatively, the LLM's access to specific tool slugs could be restricted at the agent level, or the skill could be modified to only expose a predefined, limited set of DFO operations rather than dynamic discovery and execution of all available tools.	LLM	SKILL.md:55

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d91ddbd1028d3350.svg)](https://skillshield.io/report/d91ddbd1028d3350)