Security Audit
modelry-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
modelry-automation received a trust score of 81/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Excessive Permissions via General-Purpose Tool Execution Engine, Unpinned Dependency in Manifest.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Excessive Permissions via General-Purpose Tool Execution Engine The skill relies on the 'mcp:rube' dependency, which provides access to powerful general-purpose tool execution capabilities, specifically `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. These tools allow the LLM to dynamically discover and execute a wide range of other tools and perform 'bulk ops' by running arbitrary Composio tools. This grants the skill a very broad scope of action, potentially enabling it to interact with and manipulate numerous external services if the underlying Rube MCP system is not sufficiently constrained or if the LLM is compromised. An attacker could leverage this broad access to perform unauthorized actions on connected systems. Review the scope of tools accessible via Rube MCP. Implement strict access controls and least privilege principles within the Rube MCP configuration. Ensure the LLM's use of these powerful tools is heavily constrained and monitored, and that user consent is required for sensitive operations. Consider if a more narrowly scoped set of tools could achieve the desired functionality. | LLM | SKILL.md:50 | |
| MEDIUM | Unpinned Dependency in Manifest The skill's manifest specifies a dependency on 'mcp:rube' without a version constraint. This 'unpinned' dependency means that any future update to the 'rube' skill/tool within the 'mcp' ecosystem will be automatically adopted. If a malicious or vulnerable version of 'rube' is published, this skill would inherit it without explicit review, posing a supply chain risk. This could lead to the introduction of backdoors, data exfiltration, or other security compromises. Pin the 'mcp:rube' dependency to a specific, known-good version in the manifest. Regularly review and manually update dependencies to ensure security and stability. Implement automated dependency scanning to detect known vulnerabilities. | LLM | manifest.json:1 |
Scan History
Embed Code
[](https://skillshield.io/report/9d6a8938ea2f7f41)
Powered by SkillShield