Security Audit
detrack-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
detrack-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 Access to External System.
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 Access to External System The skill grants the LLM broad access to perform various operations on the Detrack system via the Rube MCP. Tools like `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` allow dynamic discovery and execution of a wide range of Detrack operations. While this is the intended functionality for automation, it presents a significant attack surface if the LLM's control flow is compromised or if malicious input leads to unintended actions on the Detrack system. The scope of actions is limited only by the permissions of the underlying Detrack connection. Implement granular permissions for the Detrack connection within the Rube MCP. Consider requiring explicit user confirmation for sensitive or high-impact operations. Ensure robust input validation and sanitization for arguments passed to `RUBE_MULTI_EXECUTE_TOOL` to prevent abuse. Limit the scope of tools available to the LLM based on the specific use case or user roles. | LLM | SKILL.md:68 |
Scan History
Embed Code
[](https://skillshield.io/report/eaa11883276231f7)
Powered by SkillShield