Security Audit

apex27-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

apex27-automation received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Dynamic Schema Fetching from Untrusted Source.

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

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Dynamic Schema Fetching from Untrusted Source The skill explicitly instructs the LLM to dynamically fetch tool schemas, execution plans, and known pitfalls from the Rube MCP via `RUBE_SEARCH_TOOLS`. This means the operational logic and specific instructions for interacting with Apex27 are not static within the skill package but are provided by an external service (Rube MCP) at runtime. If the Rube MCP service were compromised, an attacker could serve malicious schemas, effectively injecting harmful instructions into the LLM's workflow. This could lead to data exfiltration, unintended actions, or exploitation of other vulnerabilities based on the attacker-controlled schema definitions. Implement robust validation and sandboxing for dynamically fetched schemas. Consider cryptographic signing of schemas by the trusted provider to ensure integrity. Provide a mechanism for the user or host LLM to review and approve dynamically loaded operational instructions before execution. Limit the scope of actions that can be defined by external schemas.	LLM	SKILL.md:39

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/3707b9ed109b6b42.svg)](https://skillshield.io/report/3707b9ed109b6b42)