Security Audit
boxhero-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
boxhero-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 Capabilities 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 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 Capabilities via Rube MCP The skill grants the LLM broad capabilities to execute Boxhero operations and potentially any Composio tool via `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. While intended for automation, this wide scope means that if the LLM's instructions are compromised (e.g., via prompt injection), it could perform unauthorized or malicious actions using these powerful interfaces. The `RUBE_MULTI_EXECUTE_TOOL` allows execution of any discovered Boxhero tool, and `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` suggests the ability to execute arbitrary Composio tools. Implement stricter access controls or granular permissions for the LLM's tool usage. Instead of granting access to 'any Boxhero operation' or 'any Composio tool,' consider defining a more limited set of allowed operations or requiring explicit user confirmation for high-impact actions. Ensure the underlying Rube MCP and Composio tools have robust authorization and auditing. | LLM | SKILL.md:46 |
Scan History
Embed Code
[](https://skillshield.io/report/9ab83d94bf3f9d7c)
Powered by SkillShield