Security Audit

accredible-certificates-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

accredible-certificates-automation received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.

SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 1 medium, and 1 low severity. Key findings include Broad Tool Execution Capability, Unpinned Rube MCP Dependency.

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

Manifest Analysis

100%

Static Code Analysis

91%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
MEDIUM	Broad Tool Execution Capability The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to execute tools discovered via `RUBE_SEARCH_TOOLS` or arbitrary Composio tools. This grants the LLM broad permissions to interact with the underlying Rube MCP and potentially any tool it exposes, which could extend beyond the explicit scope of 'Accredible Certificates operations' if the Rube MCP itself is misconfigured or exposes unintended functionality. This design allows for dynamic tool execution based on discovery, which inherently carries a broader permission scope than skills with fixed tool calls. Ensure the Rube MCP and the `accredible_certificates` toolkit strictly scope the available tools and their permissions to only what is necessary for Accredible Certificates automation. Implement granular access controls within the Rube MCP to limit what tools can be executed by specific skill contexts. Regularly audit the tools exposed by `RUBE_SEARCH_TOOLS` for unintended capabilities.	Static	SKILL.md:57
LOW	Unpinned Rube MCP Dependency The skill's manifest requires the `rube` MCP without specifying a version (`"mcp": ["rube"]`). This means the skill will always use the latest available version of `rube`. While this ensures access to the newest features and bug fixes, it also introduces a supply chain risk where a malicious or buggy update to `rube` could impact the skill's functionality or security without explicit review or version control. If the platform supports it, specify a pinned version or version range for the `rube` MCP in the manifest to ensure stability and allow for controlled updates, mitigating risks from unexpected changes in newer versions.	Static	SKILL.md

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/205c1a0f0cdbeca4.svg)](https://skillshield.io/report/205c1a0f0cdbeca4)