Trust Assessment
bart-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 Broad access to Bart operations via Rube MCP.
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 access to Bart operations via Rube MCP The skill allows the LLM to execute any Bart operation exposed through the Rube MCP via `RUBE_MULTI_EXECUTE_TOOL`. The documentation instructs the LLM to discover available tools using `RUBE_SEARCH_TOOLS` and then execute them using their `tool_slug`. This grants broad access to all functionalities of the Bart toolkit without specific restrictions within the skill's definition. Additionally, `RUBE_REMOTE_WORKBENCH` is mentioned for 'Bulk ops' with `run_composio_tool()`, which could imply powerful or arbitrary operations. If the Bart toolkit contains sensitive, destructive, or high-privilege operations, this broad access could lead to unintended consequences or misuse by the LLM. Consider implementing a whitelist or more granular control over which specific Bart tools can be invoked by the LLM through this skill, especially for tools with high-impact or sensitive operations. Alternatively, ensure that the underlying Bart toolkit and Rube MCP enforce appropriate authorization and scope limitations for tools exposed to LLMs. | LLM | SKILL.md:49 |
Scan History
Embed Code
[](https://skillshield.io/report/3f2da16b44cff70a)
Powered by SkillShield