Security Audit

many_chat-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

many_chat-automation received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Broad Tool Access via RUBE_REMOTE_WORKBENCH, Unverified External MCP Dependency.

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

86%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
MEDIUM	Broad Tool Access via RUBE_REMOTE_WORKBENCH The skill instructs the agent to use `RUBE_REMOTE_WORKBENCH` for 'bulk operations or data processing' by calling `run_composio_tool()` in a loop with `ThreadPoolExecutor`. This grants the agent the ability to execute arbitrary Composio tools in parallel, potentially leading to a large volume of actions or data manipulation within ManyChat if the agent's instructions are compromised. While intended for legitimate bulk operations, this capability represents a very broad and powerful tool access that could be abused. Implement granular access controls or rate limits on `RUBE_REMOTE_WORKBENCH` usage. Ensure that the `run_composio_tool()` function has robust input validation and authorization checks. Agents should be constrained to specific tool sets or operations when using bulk execution features.	Static	SKILL.md:85
MEDIUM	Unverified External MCP Dependency The skill's manifest requires `rube` as an MCP, and the `SKILL.md` instructs users to connect to `https://rube.app/mcp`. This constitutes a dependency on an external, unverified service. There is no mechanism described for ensuring the integrity or version of the tools served by `rube.app`. A compromise of the `rube.app` server could lead to the delivery of malicious tools to agents using this skill, posing a significant supply chain risk. Implement mechanisms to verify the integrity and authenticity of tools served by external MCPs (e.g., cryptographic signatures, checksums). Consider pinning to specific versions or hashes of MCP tool definitions if supported. Provide clear warnings about the risks of connecting to unverified external services.	Static	SKILL.md:23

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/1b1dd624dbd45e71.svg)](https://skillshield.io/report/1b1dd624dbd45e71)