Security Audit
placekey-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
placekey-automation received a trust score of 83/100, 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 Arbitrary Tool Execution via RUBE_REMOTE_WORKBENCH, Dependency on External Rube MCP.
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 | |
|---|---|---|---|---|
| HIGH | Potential Arbitrary Tool Execution via RUBE_REMOTE_WORKBENCH The skill documentation explicitly mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'Remote Workbench' and the ability to 'run_composio_tool()' suggest a capability to execute arbitrary tools or code within the Composio ecosystem, potentially on a remote server. Without strict sandboxing and input validation, this could allow an attacker (via prompt injection to the LLM) to execute unintended operations, access sensitive data, or perform command injection if the underlying tools permit it. The skill does not define the scope or safety mechanisms of `run_composio_tool()`, making it a high-risk component due to its broad potential capabilities. Clarify the exact capabilities and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that `run_composio_tool()` is strictly limited to a predefined set of safe operations and that its arguments are thoroughly validated. Implement strong sandboxing and least privilege principles for any code executed via this mechanism. If possible, avoid exposing such a broad 'workbench' tool to the LLM directly without explicit, fine-grained control over what can be executed. | LLM | SKILL.md:80 | |
| MEDIUM | Dependency on External Rube MCP The skill explicitly depends on the 'rube' MCP, as indicated by `"mcp": ["rube"]` in the manifest. This introduces a supply chain risk, as the security and integrity of the entire skill workflow are reliant on the trustworthiness and maintenance of the Rube MCP and its underlying infrastructure. A compromise of the Rube MCP could directly impact the security of this skill and any operations performed through it. Ensure that the Rube MCP provider (Composio/Rube) adheres to strong security practices, undergoes regular audits, and has clear incident response procedures. Monitor for any security advisories related to the Rube MCP. Consider implementing additional layers of security or isolation when interacting with external MCPs. | LLM | manifest.json:1 |
Scan History
Embed Code
[](https://skillshield.io/report/d0ab668707e1faca)
Powered by SkillShield