Security Audit
openperplex-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
openperplex-automation received a trust score of 95/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Potential Command Injection via RUBE_REMOTE_WORKBENCH.
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 | |
|---|---|---|---|---|
| MEDIUM | Potential Command Injection via RUBE_REMOTE_WORKBENCH The skill documentation introduces `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' using `run_composio_tool()`. The term 'workbench' often implies an environment where more flexible or even arbitrary code/commands can be executed. If the underlying implementation of `RUBE_REMOTE_WORKBENCH` or the `run_composio_tool()` function allows for arbitrary command execution or code evaluation, an LLM instructed to use this tool could be prompted to inject and execute malicious commands. The documentation does not provide details on input validation, sandboxing, or the specific capabilities of this 'workbench' tool, which is a common vector for command injection if not properly secured. Provide explicit documentation for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`, detailing their input schemas, execution environment, and any sandboxing or security measures in place. If arbitrary code execution is intended, clearly state the risks and provide guidance on secure usage. Otherwise, restrict inputs to prevent command injection and ensure all inputs are strictly validated against a defined schema. | LLM | SKILL.md:79 |
Scan History
Embed Code
[](https://skillshield.io/report/3b719f4ae597934c)
Powered by SkillShield