Security Audit
salesmate-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
salesmate-automation received a trust score of 92/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 1 medium, and 1 low severity. Key findings include Broad access to Salesmate operations via Rube tools, 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 17, 2026 (commit 99e2a295). 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 | Broad access to Salesmate operations via Rube tools The skill's documentation instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. `RUBE_MULTI_EXECUTE_TOOL` allows executing any Salesmate operation discovered via `RUBE_SEARCH_TOOLS`. `RUBE_REMOTE_WORKBENCH` is described for 'Bulk ops' using `run_composio_tool()`, which implies a powerful, potentially scriptable interface. This grants very broad, potentially unrestricted, control over the connected Salesmate instance. While this might be the intended functionality for a general automation skill, it represents a significant privilege that could be misused if the LLM is compromised or if the underlying Rube tools have vulnerabilities, leading to unauthorized data modification or deletion within Salesmate. Implement fine-grained access control within the Rube MCP system to restrict the specific Salesmate operations that can be performed by the skill. Provide clearer documentation on the sandboxing and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` to ensure they cannot be leveraged for arbitrary code execution or unintended operations. | LLM | SKILL.md:59 | |
| LOW | Unpinned Rube MCP dependency The skill's manifest specifies a dependency on `rube` for the MCP system (`"mcp": ["rube"]`) without a version constraint. This means that any new version of the Rube MCP system could be used, potentially introducing breaking changes, new vulnerabilities, or altered behavior without explicit review or testing. While this is a platform dependency rather than a direct code dependency, it still poses a supply chain risk. Pin the Rube MCP dependency to a specific version or version range in the `requires` field of the manifest to ensure consistent and reviewed behavior, mitigating risks from unexpected updates. | LLM | Manifest (frontmatter JSON):2 |
Scan History
Embed Code
[](https://skillshield.io/report/b87f088d44e2e9c6)
Powered by SkillShield