Trust Assessment
bart-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 Broad Tool Execution Capability.
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 | Broad Tool Execution Capability The skill instructs the AI agent to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to execute arbitrary Bart operations discovered via `RUBE_SEARCH_TOOLS`. This grants the AI agent broad, dynamic execution capabilities within the Bart system, potentially allowing it to perform any action available through the Bart toolkit. If the agent's reasoning or input is compromised, this could lead to unauthorized or malicious actions within the connected Bart environment. Implement strict access controls and sandboxing for the AI agent. Ensure that the agent's inputs are thoroughly validated and sanitized before being used in tool arguments. Limit the scope of tools discoverable by `RUBE_SEARCH_TOOLS` or restrict the permissions granted to the Bart connection if specific operations need to be constrained. | LLM | SKILL.md:39 |
Scan History
Embed Code
[](https://skillshield.io/report/992ddc61f779fb6f)
Powered by SkillShield