Security Audit
accredible-certificates-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
accredible-certificates-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 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Unpinned MCP Dependency, Broad Tool Execution Capabilities 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 20, 2026 (commit 27904475). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Unpinned MCP Dependency The skill's manifest specifies a dependency on the 'rube' MCP without a pinned version. This introduces a supply chain risk, as updates to the 'rube' MCP could introduce breaking changes or vulnerabilities without explicit review, potentially affecting the skill's security or functionality. Pin the version of the 'rube' MCP dependency in the manifest (e.g., `"rube@1.2.3"`) to ensure consistent and reviewed behavior. Regularly audit and update pinned dependencies. | Static | SKILL.md:4 | |
| MEDIUM | Broad Tool Execution Capabilities via Rube MCP The skill leverages Rube MCP, which provides powerful tools like `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` (with `run_composio_tool()`). These tools are designed for general-purpose tool orchestration and can execute arbitrary operations across various connected toolkits. While the skill's intent is specific to 'Accredible Certificates', the underlying Rube MCP system, if not properly constrained by the agent's overall permissions or Rube's internal access controls, could allow an attacker to manipulate tool slugs or arguments to execute actions beyond the intended scope, potentially accessing other connected Rube toolkits or performing unintended operations. Implement strict input validation and sanitization for all arguments passed to Rube MCP tools, especially `tool_slug` and `arguments`. Ensure the agent's execution environment or Rube MCP itself enforces least privilege, limiting the scope of tools and actions available to the agent based on its specific task. Consider using a dedicated Rube instance or configuration with only necessary toolkits enabled for this skill. | Static | SKILL.md:68 |
Scan History
Embed Code
[](https://skillshield.io/report/456789348d692062)
Powered by SkillShield