Security Audit
placekey-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
placekey-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 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Excessive Permissions: RUBE_REMOTE_WORKBENCH with potential for RCE.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Excessive Permissions: RUBE_REMOTE_WORKBENCH with potential for RCE The skill exposes the `RUBE_REMOTE_WORKBENCH` tool, which is described as enabling 'Bulk ops' via `run_composio_tool()`. The term 'remote workbench' and the generic `run_composio_tool()` function suggest a broad and potentially unconstrained execution capability on a remote system. Without clear limitations or sandboxing, this tool could be exploited for command injection, arbitrary code execution, or data exfiltration, granting excessive permissions beyond typical Placekey automation tasks. Provide explicit documentation detailing the security model, input validation, and execution environment of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If possible, replace this broad tool with more granular, purpose-specific tools that have limited capabilities. Implement strict sandboxing and access controls for any code executed through this workbench. | LLM | SKILL.md:54 |
Scan History
Embed Code
[](https://skillshield.io/report/824362e909149b0d)
Powered by SkillShield