Security Audit
mailcheck-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
mailcheck-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 Dynamic tool execution based on user input.
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 | Dynamic tool execution based on user input The skill instructs the LLM to dynamically discover tools based on a user-provided `use_case` query via `RUBE_SEARCH_TOOLS` and then execute them using `RUBE_MULTI_EXECUTE_TOOL`. Additionally, the skill references `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. If the Rube MCP system can be prompted to return tool slugs for dangerous or unintended operations (e.g., shell execution, file system access, or data exfiltration tools), or if `run_composio_tool()` allows arbitrary code execution, an attacker could craft a malicious `use_case` or manipulate the LLM's input to trick it into executing these tools. This grants excessive permissions to the LLM by enabling the execution of arbitrary, dynamically discovered, or remotely executed tools, potentially leading to command injection or data exfiltration. Implement strict allow-listing or sandboxing for tool execution. Ensure `RUBE_SEARCH_TOOLS` only returns safe, pre-approved Mailcheck-specific tools. Validate and sanitize `use_case` inputs to prevent manipulation. Implement human-in-the-loop approval for execution of potentially sensitive tools or operations. Review the capabilities of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` to ensure they cannot be exploited for arbitrary code execution. | LLM | SKILL.md:40 |
Scan History
Embed Code
[](https://skillshield.io/report/04e23230335b3e71)
Powered by SkillShield