Security Audit

sendbird-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

sendbird-automation received a trust score of 90/100, 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, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via RUBE_REMOTE_WORKBENCH.

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

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	Potential Command Injection via RUBE_REMOTE_WORKBENCH The skill describes the use of `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This tool appears to be a general-purpose execution environment. Without clear documentation on the sandboxing, input validation, and scope of `run_composio_tool()`, there is a significant risk that a malicious user could prompt the LLM to execute arbitrary commands or code within the Composio environment by manipulating the input to this tool. The skill provides no explicit warnings or safeguards against such misuse, making it a potential vector for command injection or privilege escalation if the underlying environment is not strictly controlled. Provide explicit documentation for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`, detailing its security model, sandboxing, input validation, and any limitations on code execution. If it allows arbitrary code, implement strict input sanitization and user consent mechanisms. Advise the LLM to only use this tool with highly trusted, pre-defined operations and ensure user input is never directly passed to `run_composio_tool()` without rigorous validation.	LLM	SKILL.md:60

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/25979d7c0c0131a7.svg)](https://skillshield.io/report/25979d7c0c0131a7)