Security Audit
templated-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
templated-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 Potential for Excessive Permissions via RUBE_REMOTE_WORKBENCH, Hardcoded Dependency on External MCP (rube.app) Introduces Supply Chain Risk.
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 | Hardcoded Dependency on External MCP (rube.app) Introduces Supply Chain Risk The skill explicitly instructs users to add `https://rube.app/mcp` as an MCP server. This hardcodes a dependency on a specific external, third-party service for core functionality. The statement 'No API keys needed — just add the endpoint and it works' further highlights an implicit trust in `rube.app` without explicit authentication for the MCP itself. If `rube.app` were to be compromised or become malicious, it could directly impact the security and integrity of operations performed by agents using this skill, leading to data exfiltration, command injection, or other severe security breaches. Advise users to thoroughly vet third-party services like `rube.app` before integration. Implement mechanisms for verifying the integrity and authenticity of the MCP endpoint. If possible, provide options for self-hosting or using trusted, authenticated MCP instances. Clearly document the security implications of integrating with external services and the level of trust required. | LLM | SKILL.md:20 | |
| MEDIUM | Potential for Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill documentation recommends using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`. The term 'REMOTE_WORKBENCH' and the ability to 'run_composio_tool()' suggest a powerful capability that could execute arbitrary operations or tools within a remote environment. This implies broad permissions that, if not properly scoped or if the underlying workbench is compromised, could lead to excessive access or unintended actions. The skill itself doesn't define the scope of these operations, making it difficult to assess the full extent of potential permissions. Clarify the exact scope and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Provide guidance on how users can restrict its permissions or ensure it operates within a least-privilege context. If possible, avoid recommending tools with overly broad capabilities without strong justification and safeguards. | LLM | SKILL.md:60 |
Scan History
Embed Code
[](https://skillshield.io/report/09b993a405e1d65c)
Powered by SkillShield