Security Audit
fullenrich-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
fullenrich-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 Execution Capability 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 Tool Execution Capability via Rube MCP The skill provides the LLM with the `RUBE_MULTI_EXECUTE_TOOL` capability, which allows the execution of any discovered `fullenrich` tool with arbitrary, schema-compliant arguments. While this is the intended functionality for an automation skill, it grants the LLM a very broad scope of action within the `fullenrich` ecosystem. If the `fullenrich` toolkit contains tools capable of sensitive, destructive, or data-access operations, an LLM misdirection or prompt injection could lead to unintended and potentially harmful actions. The skill itself does not implement granular control over which specific `fullenrich` tools can be executed, relying on the LLM's interpretation of `RUBE_SEARCH_TOOLS` results. Implement more granular control or explicit allow-lists for specific `fullenrich` tools that the LLM is permitted to execute. Alternatively, ensure robust human-in-the-loop approval for sensitive operations, or restrict the LLM's access to only non-destructive `fullenrich` tools. The `RUBE_SEARCH_TOOLS` output could be filtered before presenting to the LLM for execution. | LLM | SKILL.md:56 |
Scan History
Embed Code
[](https://skillshield.io/report/071f85594732e3df)
Powered by SkillShield