Security Audit

codereadr-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

codereadr-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 Broad Rube MCP access requested, Unversioned 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 20, 2026 (commit 27904475). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

78%

Behavioral Risk Signals

Network Access

2 findings

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad Rube MCP access requested The skill's manifest `requires: {"mcp": ["rube"]}` grants access to the entire Rube MCP. While the skill's stated purpose is "Codereadr automation", the Rube MCP is a general platform that can expose tools for various services. This broad permission means the skill could potentially access and operate tools beyond the intended Codereadr scope, depending on what other capabilities the Rube MCP exposes. This creates an attack surface where an agent could be prompted to use non-Codereadr tools via this skill, leading to unintended actions or data exposure. Restrict the `requires` field to only the specific Rube MCP tools or toolkits necessary for Codereadr operations, if such granular control is available (e.g., `{"mcp": ["rube:codereadr"]}` or similar scoped permissions).	LLM	composio-skills/codereadr-automation/SKILL.md:1
MEDIUM	Unversioned Rube MCP dependency The skill depends on the Rube MCP (`requires: {"mcp": ["rube"]}`) without specifying a version. This means the skill will always use the latest version of the Rube MCP available at `https://rube.app/mcp`. Future updates to Rube MCP could introduce breaking changes, security vulnerabilities, or even malicious functionality, which would automatically affect this skill without explicit review or control. This constitutes an unpinned dependency supply chain risk. If Rube MCP supports versioning or specific endpoint versions, update the `requires` field to pin to a known, stable, and reviewed version of the Rube MCP to mitigate risks from unexpected changes or vulnerabilities in future versions.	LLM	composio-skills/codereadr-automation/SKILL.md:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/a984cdf3b9406291.svg)](https://skillshield.io/report/a984cdf3b9406291)