Security Audit
botpress-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
botpress-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 Excessive Permissions 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 20, 2026 (commit 27904475). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill exposes a tool named `RUBE_REMOTE_WORKBENCH` which is described as being for 'Bulk ops' and using `run_composio_tool()`. The term 'workbench' typically implies a flexible, potentially scriptable, or interactive environment, and 'bulk ops' suggests broad operational capabilities. Without explicit documentation detailing the specific limitations and security controls of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`, this tool presents a high risk of excessive permissions. A compromised LLM could potentially leverage this tool to execute arbitrary or highly privileged operations within the Botpress environment or even the underlying Composio platform, leading to data manipulation, deletion, or unauthorized access. Provide explicit documentation for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` detailing their exact capabilities, scope, and any security limitations. If `run_composio_tool()` allows arbitrary code execution or highly privileged operations, consider removing it or restricting its access to specific, pre-approved functions. Implement strict input validation and sandboxing for any operations performed by this tool. Ensure the LLM is explicitly instructed on the safe and limited use of this tool, if it must be exposed. | LLM | SKILL.md:60 |
Scan History
Embed Code
[](https://skillshield.io/report/9752dc23791f6c6a)
Powered by SkillShield