Security Audit
documenso-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
documenso-automation received a trust score of 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Broad Tool Execution Capabilities via Rube MCP, Unpinned Rube MCP Dependency.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Broad Tool Execution Capabilities via Rube MCP The skill leverages `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` from the Rube MCP. These tools are designed for generic execution of other tools, including `run_composio_tool()`. This grants the AI agent using this skill very broad capabilities, potentially allowing it to execute any operation available through the Rube MCP and Composio ecosystem, not just Documenso-specific tasks, if not properly scoped by the Rube MCP configuration. This broad access increases the attack surface if the agent is compromised or misused. Implement strict access controls and least privilege principles for the AI agent. Ensure the Rube MCP is configured with the narrowest possible scope of tools and permissions for this specific skill. Consider using a dedicated Rube instance or configuration that only exposes Documenso-related tools. | LLM | SKILL.md:60 | |
| MEDIUM | Unpinned Rube MCP Dependency The skill's manifest specifies a dependency on the 'rube' MCP (`"mcp": ["rube"]`) without a specific version or hash. This means the skill will accept any version of the Rube MCP. If a malicious or vulnerable update to the Rube MCP were to be released, the skill could automatically load and use it, introducing a supply chain vulnerability. Pin the Rube MCP dependency to a specific, known-good version or hash in the manifest to prevent automatic updates to potentially malicious or vulnerable versions. Regularly review and update the pinned version after security vetting. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/1b9aee1553918e03)
Powered by SkillShield