Security Audit
cardly-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
cardly-automation received a trust score of 93/100, 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 Broad tool execution capability via Rube MCP.
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 | Broad tool execution capability via Rube MCP The skill's documentation instructs the agent to use Rube MCP tools such as `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. These tools provide generic interfaces for executing arbitrary Composio tools by their slug or via programmatic calls (`run_composio_tool()`). While the skill's stated purpose is Cardly automation, the underlying mechanism grants the agent broad access to execute any tool available through Rube, potentially exceeding the minimum necessary permissions for Cardly-specific tasks. A compromised agent could leverage this broad access to interact with other Composio toolkits if Rube is configured to expose them, leading to unintended actions or data manipulation beyond the scope of Cardly. Implement stricter access controls within Rube MCP to limit the agent's ability to only Cardly-specific tools. Alternatively, if the agent's environment allows, constrain the agent's execution context to prevent misuse of generic tool execution capabilities. If possible, use more granular Rube tools that are specifically scoped to Cardly operations rather than generic tool executors. | Static | SKILL.md:49 |
Scan History
Embed Code
[](https://skillshield.io/report/7ba9906d624e00f1)
Powered by SkillShield