Security Audit
recruitee-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
recruitee-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 Potential Command Injection / Excessive Permissions 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 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 | Potential Command Injection / Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill documentation mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'workbench' often implies an environment where arbitrary code or commands can be executed. If this tool allows the LLM to execute unconstrained code or shell commands, it presents a significant command injection vulnerability and grants excessive permissions to the skill. Without further details on the `RUBE_REMOTE_WORKBENCH`'s sandboxing and input validation, this is a high-risk primitive. Provide clear documentation on the security model, sandboxing, and input validation of `RUBE_REMOTE_WORKBENCH`. Ensure it does not allow arbitrary code execution or shell commands. If it is intended for controlled execution, specify the exact scope and limitations, and ensure all inputs are strictly validated and sanitized. | LLM | SKILL.md:71 |
Scan History
Embed Code
[](https://skillshield.io/report/6d0699574d690770)
Powered by SkillShield