Security Audit
cdr-platform-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
cdr-platform-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 Skill exposes generic 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 | Skill exposes generic tool execution via RUBE_REMOTE_WORKBENCH The skill documentation describes the use of `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This suggests a generic capability to execute arbitrary Composio tools, not just those specific to the `cdr_platform` toolkit. If the underlying Rube MCP grants broad access to various Composio tools, this could lead to excessive permissions for the AI agent, enabling it to perform actions beyond its intended scope or interact with unauthorized systems. Restrict the scope of `RUBE_REMOTE_WORKBENCH` to specific, pre-approved toolkits or operations within the Rube MCP configuration. Alternatively, if `run_composio_tool()` is intended to be generic, ensure that the agent's access to `RUBE_REMOTE_WORKBENCH` is carefully controlled and monitored, and that the agent's overall permissions are minimized to prevent unintended actions. | LLM | SKILL.md:79 |
Scan History
Embed Code
[](https://skillshield.io/report/eab3335d01b5f4b6)
Powered by SkillShield