Security Audit
geokeo-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
geokeo-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, 0 high, 1 medium, and 0 low severity. Key findings include Exposure of potentially broad '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 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 | |
|---|---|---|---|---|
| MEDIUM | Exposure of potentially broad 'Remote Workbench' tool The skill exposes `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'remote workbench' and the generic `run_composio_tool()` function suggest a capability that might allow for arbitrary or overly broad operations beyond specific Geokeo automation tasks. If `run_composio_tool()` can execute arbitrary code, access unrelated systems, or perform actions outside the intended scope of Geokeo, this could lead to excessive permissions for the LLM, potentially enabling unauthorized actions or data manipulation. Clarify the exact scope and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure it is strictly confined to necessary Geokeo operations and does not allow arbitrary code execution or access to unrelated systems. If possible, provide more granular tools for specific bulk operations instead of a generic 'workbench' to limit the blast radius of potential misuse. | LLM | SKILL.md:65 |
Scan History
Embed Code
[](https://skillshield.io/report/944153d322aaa014)
Powered by SkillShield