Trust Assessment
here-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 Broad Tool Execution Capability 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 | Broad Tool Execution Capability via RUBE_REMOTE_WORKBENCH The skill instructs the agent to use `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. This tool, by its nature, suggests the ability to execute arbitrary Composio tools, not just those specific to 'Here' operations. If the agent is intended to be restricted solely to 'Here' operations, providing access to `RUBE_REMOTE_WORKBENCH` could grant broader permissions than necessary. A compromised agent could potentially interact with other connected Composio toolkits or perform actions outside the intended 'Here' scope. Clarify the exact scope of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it can execute tools beyond the 'Here' toolkit, provide guidance on how to restrict its usage or consider if a more scoped tool is appropriate for a skill primarily focused on 'Here' operations. Ensure that agents are only granted access to the minimum necessary tools. | LLM | SKILL.md:59 |
Scan History
Embed Code
[](https://skillshield.io/report/290f5d0680cda6ff)
Powered by SkillShield