Security Audit
similarweb_digitalrank_api-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
similarweb_digitalrank_api-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 2 findings: 0 critical, 1 high, 0 medium, and 1 low severity. Key findings include Potential for Command Injection via RUBE_REMOTE_WORKBENCH, 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 | Potential for Command Injection via RUBE_REMOTE_WORKBENCH The skill recommends using `RUBE_REMOTE_WORKBENCH` for 'bulk operations or data processing' and explicitly mentions using `run_composio_tool()` in a loop with `ThreadPoolExecutor`. This implies the ability to execute arbitrary code within the workbench environment. If the `RUBE_REMOTE_WORKBENCH` is not adequately sandboxed and its inputs (e.g., code for `run_composio_tool()` or `ThreadPoolExecutor`) are not strictly validated and sanitized, an attacker could potentially inject and execute arbitrary commands or code. This could lead to data exfiltration, system compromise, or other malicious activities. Ensure the `RUBE_REMOTE_WORKBENCH` environment is strictly sandboxed, with no access to sensitive system resources or network locations beyond its intended scope. Implement robust input validation and sanitization for any code or commands passed to `run_composio_tool()` or executed within the `ThreadPoolExecutor`. Consider restricting the types of operations allowed within the workbench to a predefined, safe set. | LLM | SKILL.md:67 | |
| LOW | Unpinned Rube MCP dependency The skill manifest declares a dependency on the `rube` MCP (`"mcp": ["rube"]`) and the `SKILL.md` instructs users to add `https://rube.app/mcp` as an MCP server. However, no specific version or content hash is pinned for the `rube` MCP. This lack of version pinning means that updates to the `rube` MCP could introduce breaking changes or, in a worst-case scenario, malicious code without explicit review or approval, posing a supply chain risk. Implement version pinning or content hashing for the `rube` MCP dependency to ensure that a consistent and verified version is always used. This helps prevent unexpected changes or malicious updates from affecting the skill's security and functionality. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/1c1d357a9268c2d2)
Powered by SkillShield