Security Audit

sendbird-ai-chabot-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

sendbird-ai-chabot-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 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

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad Tool Execution via Rube MCP The skill instructs the AI to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` which enable the execution of any tool discovered via `RUBE_SEARCH_TOOLS`. This grants the AI broad, dynamic access to perform operations within the Sendbird AI Chabot toolkit (and potentially others via `RUBE_REMOTE_WORKBENCH`). While the skill advises dynamic discovery, the underlying mechanism allows for high-privilege operations without explicit, granular permission checks at the skill level. An attacker exploiting a prompt injection could leverage this to execute arbitrary actions. Implement more granular access control for tool execution. Instead of allowing execution of any discovered tool, restrict the set of executable tools to a predefined, minimal list required for the skill's specific purpose. If `RUBE_REMOTE_WORKBENCH` is not strictly necessary, consider removing its instruction. Ensure that the Composio platform itself has robust authorization and auditing for tool executions.	LLM	SKILL.md:40

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/778262f91ffc432c.svg)](https://skillshield.io/report/778262f91ffc432c)