Trust Assessment
deel-automation received a trust score of 90/100, 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, 1 high, 0 medium, and 0 low severity. Key findings include Skill exposes potentially overly permissive 'RUBE_REMOTE_WORKBENCH' tool.
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 | Skill exposes potentially overly permissive 'RUBE_REMOTE_WORKBENCH' tool The skill documentation lists `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'workbench' often implies a flexible, potentially arbitrary code execution or scripting environment. If `RUBE_REMOTE_WORKBENCH` allows for arbitrary code execution or highly privileged operations without strict sandboxing or input validation, then granting the LLM access to this skill provides it with excessive permissions. A malicious prompt could instruct the LLM to leverage this tool to execute unauthorized commands, access sensitive data, or perform other harmful actions within the Deel environment or the underlying system, even if the specific malicious arguments are not detailed in this documentation. The risk lies in the broad capabilities potentially exposed by this tool. Clarify the exact capabilities and security boundaries of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it allows arbitrary code execution, consider if this level of access is necessary for the skill. Implement strict input validation and sandboxing for `RUBE_REMOTE_WORKBENCH` to prevent command injection or unauthorized data access. If possible, provide a more constrained tool for 'Bulk ops' that doesn't expose a general-purpose execution environment. | LLM | SKILL.md:67 |
Scan History
Embed Code
[](https://skillshield.io/report/eb3c3bd0d5aab0c2)
Powered by SkillShield