Security Audit
cloudflare-browser-rendering-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
cloudflare-browser-rendering-automation received a trust score of 95/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 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 17, 2026 (commit 99e2a295). 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 | Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill documentation indicates that `RUBE_REMOTE_WORKBENCH` can be used with `run_composio_tool()`. This suggests that the LLM, through this single entry point, might be able to execute arbitrary Composio tools beyond the scope of Cloudflare Browser Rendering. If `run_composio_tool()` allows invocation of any tool within the Composio ecosystem, this grants excessively broad permissions to the LLM, potentially enabling actions not intended for this specific skill. If `run_composio_tool()` is intended to be restricted to a specific set of tools (e.g., only Cloudflare Browser Rendering tools), the Rube MCP system should enforce this restriction. Alternatively, the documentation should explicitly clarify the scope and potential implications of using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`, or provide a more granular tool for bulk operations if broad access is not desired. | LLM | SKILL.md:68 |
Scan History
Embed Code
[](https://skillshield.io/report/e99de499e26c25be)
Powered by SkillShield