Security Audit
builtwith-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
builtwith-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, 0 high, 1 medium, and 0 low severity. Key findings include Broad tool access 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 | |
|---|---|---|---|---|
| MEDIUM | Broad tool access via RUBE_REMOTE_WORKBENCH The skill is described as 'Builtwith automation' in its manifest and primary description. However, it exposes the `RUBE_REMOTE_WORKBENCH` tool, which, when used with `run_composio_tool()`, typically allows execution of any Composio tool, not just Builtwith-specific operations. This could grant the AI agent broader access and capabilities than intended or necessary for the skill's stated purpose, potentially leading to unintended actions or access to other toolkits. If the skill's intended scope is strictly Builtwith automation, consider removing or restricting access to `RUBE_REMOTE_WORKBENCH` within this skill's context. Alternatively, ensure that `run_composio_tool()` is strictly scoped to Builtwith operations when invoked through this skill. If broader access is intended, clarify this in the skill's description to accurately reflect its capabilities. | LLM | SKILL.md:80 |
Scan History
Embed Code
[](https://skillshield.io/report/3b1b6b92771aedcc)
Powered by SkillShield