Security Audit

smtp2go-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

smtp2go-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 Tool Access to Smtp2go API, Unpinned External 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

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad Tool Access to Smtp2go API The skill grants the LLM broad access to Smtp2go operations through `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. These tools allow the LLM to discover and execute any function exposed by the Smtp2go toolkit via Rube MCP. While this is the intended functionality for automating Smtp2go tasks, it means a compromised LLM (e.g., via prompt injection) could perform any Smtp2go operation, including sending unauthorized emails, modifying account settings, or accessing sensitive data, without further internal restrictions from the skill itself. Implement internal guardrails within the skill to limit the scope of operations an LLM can perform, or require explicit user confirmation for sensitive actions. Clearly document the full scope of access granted to the LLM.	LLM	SKILL.md:60
MEDIUM	Unpinned External MCP Dependency The skill relies on the 'rube' MCP (`https://rube.app/mcp`) as an external dependency, declared in the manifest and referenced in the skill description. There is no version pinning or hash verification specified for the Rube MCP. This introduces a supply chain risk, as a compromise of the `rube.app` service or the Rube MCP itself could impact the security and integrity of this skill's operations without the ability to detect or prevent changes to the dependency. If the platform supports it, specify a version or hash for the Rube MCP dependency to ensure deterministic and verifiable execution. Regularly monitor the security posture of external dependencies.	LLM	SKILL.md:26

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/fd1ef2c84785f768.svg)](https://skillshield.io/report/fd1ef2c84785f768)