Security Audit
async-interview-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
async-interview-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 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 Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill mentions `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. The term 'workbench' and the ability to 'run_composio_tool()' suggest a broad execution capability that could allow the LLM to execute arbitrary Composio tools or potentially arbitrary code if not properly constrained. This grants excessive permissions beyond the stated purpose of 'Async Interview automation' and could be exploited for unintended operations or resource access. Clarify and restrict the scope of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure it can only execute a predefined, whitelisted set of tools or operations directly relevant to 'Async Interview automation' and does not allow for arbitrary code execution or access to unrelated systems. Provide a detailed schema for `RUBE_REMOTE_WORKBENCH` that explicitly limits its capabilities. | LLM | SKILL.md:68 |
Scan History
Embed Code
[](https://skillshield.io/report/011bfd1e56ceb3c3)
Powered by SkillShield