Security Audit
mboum-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
mboum-automation received a trust score of 82/100, 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, 1 high, 1 medium, and 0 low severity. Key findings include Highly privileged tool `RUBE_REMOTE_WORKBENCH` exposes command injection risk, External authentication flow introduces phishing 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
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Highly privileged tool `RUBE_REMOTE_WORKBENCH` exposes command injection risk The skill recommends using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This tool appears to allow execution of arbitrary Composio tools or custom code within the Rube environment. If an attacker can inject arguments into `run_composio_tool()`, they could potentially execute arbitrary commands, access sensitive data, or perform unauthorized actions, leading to command injection and data exfiltration. The skill does not provide sufficient warnings or safeguards for this powerful capability. Implement strict input validation and sanitization for arguments passed to `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Clearly document the security implications and potential risks of using this highly privileged tool. Consider restricting its use or requiring explicit user confirmation for sensitive operations. | LLM | SKILL.md:60 | |
| MEDIUM | External authentication flow introduces phishing risk The skill instructs the agent to 'follow the returned auth link to complete setup' for Mboum connections via `RUBE_MANAGE_CONNECTIONS`. While this is a standard authentication pattern, it relies on the trustworthiness of the `RUBE_MANAGE_CONNECTIONS` tool and the Rube MCP to provide a legitimate link. A compromised Rube MCP or a malicious `mboum` toolkit could return a phishing link, leading to credential harvesting if the agent or user is not vigilant. Advise users to verify the legitimacy of any authentication links before proceeding. Implement mechanisms within the agent to validate the domain of authentication links against a known safe list or to warn users about suspicious URLs. | LLM | SKILL.md:29 |
Scan History
Embed Code
[](https://skillshield.io/report/d1b77ad2365f3b14)
Powered by SkillShield