Security Audit
bench-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
bench-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, 0 high, 2 medium, and 0 low severity. Key findings include Unpinned dependency in manifest, Broad tool execution capability via RUBE_REMOTE_WORKBENCH.
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 | |
|---|---|---|---|---|
| MEDIUM | Unpinned dependency in manifest The skill manifest specifies a dependency on 'rube' without a version constraint. This means that any future version of the 'rube' MCP could be loaded, including potentially malicious or incompatible updates, without explicit review. This introduces a supply chain risk. Pin the dependency 'rube' to a specific version or version range in the `requires` section of the manifest to ensure stability and security. Example: `{"requires": {"mcp": ["rube==1.2.3"]}}` or `{"requires": {"mcp": ["rube>=1.0.0,<2.0.0"]}}`. | LLM | SKILL.md | |
| MEDIUM | Broad tool execution capability via RUBE_REMOTE_WORKBENCH The skill describes using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This suggests a generic capability to execute arbitrary Composio tools. If the underlying Composio tools (especially those within the 'bench' toolkit or other accessible toolkits) have broad permissions (e.g., filesystem access, arbitrary network requests, or sensitive data manipulation), this skill could inherit and leverage those permissions without specific constraints. The skill's documentation does not specify any limitations on which tools can be executed or what their scope is when called via `run_composio_tool()`. Implement stricter controls or documentation to limit the scope of tools that can be executed via `RUBE_REMOTE_WORKBENCH` or `run_composio_tool()`. Clearly define the permissions and potential side effects of the underlying Composio tools, and ensure the skill only calls tools with the minimum necessary privileges for its stated purpose. If possible, restrict `run_composio_tool()` to a whitelist of safe operations. | LLM | SKILL.md:80 |
Scan History
Embed Code
[](https://skillshield.io/report/53a51d89e2ffc173)
Powered by SkillShield