Security Audit
campaign-cleaner-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
campaign-cleaner-automation received a trust score of 86/100, 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 Explicit dependency on unverified external MCP endpoint.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Explicit dependency on unverified external MCP endpoint The skill explicitly instructs the LLM to connect to `https://rube.app/mcp` as an MCP server. This introduces a significant supply chain risk, as the integrity and security of the `rube.app` service are not verified. A compromised or malicious MCP could serve malicious tool schemas, execute arbitrary code via tools like `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH`, or facilitate data exfiltration through its provided tools. The skill implicitly trusts this external endpoint. Implement mechanisms to verify the authenticity and integrity of external MCPs before connecting. Consider using a trusted, sandboxed environment for executing tools from external sources. Provide clear warnings to users about the risks of connecting to unverified endpoints. If possible, specify a version or hash for the MCP configuration to prevent unexpected changes. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/c276d3e7f62c7f9c)
Powered by SkillShield