Trust Assessment
u301-automation received a trust score of 86/100, 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 Excessive Permissions via Meta-Tool Usage.
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 | |
|---|---|---|---|---|
| HIGH | Excessive Permissions via Meta-Tool Usage The skill `u301-automation` leverages the Rube MCP (Meta-Tool Control Plane) which inherently grants broad capabilities to the LLM. The skill instructs the LLM to use `RUBE_SEARCH_TOOLS` to discover available tools and `RUBE_MULTI_EXECUTE_TOOL` to execute them. Additionally, it mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for bulk operations. This means that by adopting this skill, the LLM gains the ability to discover and execute potentially any tool exposed by the Rube MCP, not just those related to U301. This broad access to an entire ecosystem of tools (Composio) goes beyond the stated purpose of 'U301 automation' and could lead to unauthorized actions or data access if the Rube MCP has connections to sensitive systems. To mitigate this, consider the following: 1. **Restrict Rube MCP Scope**: Configure the Rube MCP instance used by the agent to expose only U301-specific tools, or a strictly limited set of tools relevant to the skill's intended function. 2. **Skill-Level Tool Whitelisting**: If possible, modify the skill's internal logic (if it were code) to explicitly whitelist or validate tool slugs before execution, rather than relying solely on discovery. 3. **Clear Documentation of Scope**: Explicitly document the full scope of capabilities granted by the Rube MCP dependency, even if the skill's primary use case is narrower, to ensure users understand the potential reach. | LLM | SKILL.md:39 |
Scan History
Embed Code
[](https://skillshield.io/report/7335a2557b49f986)
Powered by SkillShield