Security Audit
brightdata-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
brightdata-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 Broad tool execution 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 | Broad tool execution via RUBE_REMOTE_WORKBENCH The skill documentation mentions `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' using `run_composio_tool()`. This function name suggests the ability to execute arbitrary tools within the broader Composio ecosystem, not just those related to Brightdata. If `run_composio_tool()` is not strictly scoped to Brightdata-specific operations, an LLM using this skill could potentially invoke other Composio tools that have broader permissions (e.g., file system access, arbitrary network requests, access to other sensitive APIs). This could lead to data exfiltration, unauthorized actions, or privilege escalation beyond the intended scope of Brightdata automation, bypassing the more controlled `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL` workflow. 1. **Restrict `RUBE_REMOTE_WORKBENCH`**: Ensure that the `RUBE_REMOTE_WORKBENCH` tool, when invoked through this skill, is strictly limited to executing only Brightdata-specific Composio tools. 2. **Clarify documentation**: If `run_composio_tool()` is indeed generic, the skill's documentation should explicitly warn about its broad capabilities and provide clear instructions or guardrails to prevent its misuse for non-Brightdata operations. 3. **Implement runtime checks**: The Rube MCP should enforce strict access control and scope limitations for `run_composio_tool()` based on the calling skill's declared purpose. | LLM | SKILL.md:66 |
Scan History
Embed Code
[](https://skillshield.io/report/c7c4082245f0f269)
Powered by SkillShield