Security Audit
nano-nets-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
nano-nets-automation received a trust score of 96/100, 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 Ambiguous 'RUBE_REMOTE_WORKBENCH' tool may allow excessive permissions or command injection.
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 | Ambiguous 'RUBE_REMOTE_WORKBENCH' tool may allow excessive permissions or command injection The skill documentation mentions `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. The term 'workbench' often implies an environment with broader execution capabilities, potentially allowing arbitrary code execution (e.g., Python scripts, shell commands) or access to a wider range of system resources than standard tool calls. If `run_composio_tool()` within this workbench context permits execution beyond the scope of defined Composio tools, it could lead to command injection or excessive permissions, allowing an attacker to execute arbitrary commands on the host system or access sensitive data. Clarify the exact capabilities and security boundaries of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Specify if it's a sandboxed environment, what types of operations are permitted, and if it allows arbitrary code execution. If arbitrary code is allowed, implement strict input validation and execution sandboxing. If not, update the documentation to explicitly state its limitations and ensure the underlying implementation enforces these restrictions. | LLM | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/42d6b4e9690739d7)
Powered by SkillShield