Security Audit
builtwith-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
builtwith-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 Excessive Permissions via RUBE_REMOTE_WORKBENCH, Excessive Permissions via RUBE_MANAGE_CONNECTIONS.
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 | Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill documentation mentions the use of `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'workbench' and the generic nature of `run_composio_tool()` suggest a broad capability, potentially allowing arbitrary code execution or complex operations on a remote system. Without explicit constraints on what `run_composio_tool()` can execute or access, this tool presents a significant risk of excessive permissions. An attacker manipulating the agent could potentially leverage this to execute unauthorized commands or perform extensive data manipulation on a remote system. Provide clear documentation and enforce strict limitations on the capabilities of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Specify exactly what types of operations are permitted and what resources can be accessed. Implement granular access controls and require explicit user confirmation for sensitive 'bulk operations'. | LLM | SKILL.md:60 | |
| MEDIUM | Excessive Permissions via RUBE_MANAGE_CONNECTIONS The skill instructs the agent to use `RUBE_MANAGE_CONNECTIONS` to manage connections to external services (specifically Builtwith). While new connections are stated to require user interaction via an auth link, the ability to manage (e.g., modify, delete, or switch) existing connections to external services without explicit, granular user confirmation for each action could lead to unauthorized access, denial of service, or redirection to malicious services if an attacker can manipulate the agent's use of this tool. Implement strict access controls and require explicit user confirmation for any modification, deletion, or switching of existing connections via `RUBE_MANAGE_CONNECTIONS`. Ensure that the tool's scope is limited to only necessary connection management actions and that it cannot be used to connect to arbitrary, unvetted services. | LLM | SKILL.md:19 |
Scan History
Embed Code
[](https://skillshield.io/report/4477a8fac3c7599e)
Powered by SkillShield