Security Audit

chatwork-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

chatwork-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 from External Service Introduces Supply Chain Risk.

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

85%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Dynamic Tool Discovery from External Service Introduces Supply Chain Risk The skill instructs the LLM to dynamically discover and execute tools from an external service (`https://rube.app/mcp`) via `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL`. This means the effective capabilities and behavior of the skill are entirely dependent on the integrity and security of the `rube.app` service. A compromise of `rube.app` could lead to the LLM being instructed to execute malicious Chatwork operations (e.g., data exfiltration, unauthorized modifications, sending spam) without any change to the skill's local definition. The skill explicitly encourages this dynamic behavior ('Always search tools first') as a core workflow pattern, making it a critical dependency. Implement robust vetting and continuous monitoring of the `rube.app` service and the tools it serves. Consider mechanisms to pin tool versions or schemas, or to require explicit human approval for new or significantly changed tool capabilities, rather than relying solely on dynamic discovery and execution. Reduce the scope of permissions granted to the LLM when interacting with dynamically discovered tools.	Static	SKILL.md:13

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/9b06732623f68968.svg)](https://skillshield.io/report/9b06732623f68968)