Security Audit

zoho-invoice-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

zoho-invoice-automation received a trust score of 83/100, 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 execution via RUBE_REMOTE_WORKBENCH, Unpinned external service dependencies.

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

78%

Behavioral Risk Signals

Network Access

2 findings

Filesystem Write

1 finding

Shell Execution

2 findings

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad tool execution via RUBE_REMOTE_WORKBENCH The skill description explicitly mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This implies the ability to execute arbitrary Composio tools, not just those specifically related to Zoho Invoice. If Composio provides tools with broad system access (e.g., filesystem access, network operations, or arbitrary code execution), this could lead to excessive permissions being granted to the agent using this skill, potentially enabling command injection or data exfiltration beyond the intended scope of Zoho Invoice automation. Restrict the scope of `RUBE_REMOTE_WORKBENCH` to only Zoho Invoice-specific operations or clearly document the full extent of permissions granted by `run_composio_tool()` and its potential risks. If `run_composio_tool()` is intended to be limited to the `zoho_invoice` toolkit, this should be explicitly stated and enforced within the skill's definition or the underlying MCP.	LLM	SKILL.md:67
MEDIUM	Unpinned external service dependencies The skill relies on external services `https://rube.app/mcp` and `composio.dev` toolkits. These dependencies are not version-pinned or subject to integrity checks. A compromise or unannounced change to these external services could introduce vulnerabilities or malicious behavior into the skill's execution without explicit updates or review by the skill author, posing a supply chain risk. Implement version pinning or integrity checks for external services where technically feasible. If direct pinning is not possible, regularly monitor the external services for changes and document the potential risks associated with unversioned dependencies. Consider using a proxy or gateway that can enforce versioning or content integrity.	LLM	SKILL.md:18

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/c53c60d7f4d93083.svg)](https://skillshield.io/report/c53c60d7f4d93083)