Security Audit
espocrm-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
espocrm-automation received a trust score of 81/100, 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 Broad tool execution via RUBE_REMOTE_WORKBENCH, Reliance on external Rube/Composio ecosystem 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 20, 2026 (commit 27904475). 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 | Broad tool execution via RUBE_REMOTE_WORKBENCH The skill exposes `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`, which allows the LLM to execute arbitrary Composio tools. This grants broad permissions, enabling potential command injection, data exfiltration, or other malicious actions if a Composio tool is compromised or designed maliciously. The skill itself does not restrict which tools can be run via this mechanism, making the LLM vulnerable to executing unintended or harmful operations through the Composio ecosystem. Restrict the scope of `RUBE_REMOTE_WORKBENCH` to a predefined, allow-listed set of safe Composio tools, or provide clear guidelines and guardrails for its use. Implement strict input validation and sandboxing for any tools executed via this mechanism to prevent abuse. | LLM | SKILL.md:59 | |
| MEDIUM | Reliance on external Rube/Composio ecosystem introduces supply chain risk The skill is entirely dependent on the security and integrity of the Rube MCP and Composio toolkits. The `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` functions allow the execution of tools provided by this external ecosystem. A compromise or malicious tool within the Composio ecosystem could lead to severe security vulnerabilities, including data exfiltration or command injection, when executed via this skill. The skill's functionality is directly tied to the trustworthiness of these third-party components. Implement robust vetting processes for all third-party tools and services. Regularly audit the security of the Rube MCP and Composio toolkits. Consider implementing runtime monitoring and sandboxing for tool executions to mitigate risks from compromised external components. Clearly document the security posture and update mechanisms of these external dependencies. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/10db162f0618a92f)
Powered by SkillShield