Security Audit

shotstack-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

shotstack-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 via Rube MCP, Unpinned External Service Dependency (Rube MCP).

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

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad Tool Access via Rube MCP The skill grants the agent broad access to external services through the Rube MCP tools. Specifically, `RUBE_MULTI_EXECUTE_TOOL` allows the execution of any Shotstack operation discovered via `RUBE_SEARCH_TOOLS`. Furthermore, `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` suggests a general-purpose execution environment for potentially any Composio tool. This level of access means a compromised or misused agent could perform a wide range of actions on the connected Shotstack account (e.g., create, modify, delete projects, manage assets) and potentially other services if `RUBE_REMOTE_WORKBENCH` is not strictly scoped. While intended for automation, this broad access increases the attack surface. Implement fine-grained access control for the Rube MCP tools, if possible, to limit the specific Shotstack operations an agent can perform. For `RUBE_REMOTE_WORKBENCH`, ensure that `run_composio_tool()` is strictly sandboxed and limited to a predefined, minimal set of safe operations. Provide clear documentation on the exact scope of actions each tool can perform.	LLM	SKILL.md:50
MEDIUM	Unpinned External Service Dependency (Rube MCP) The skill relies on an external, unversioned service endpoint `https://rube.app/mcp` for its core functionality. This constitutes a supply chain risk because the skill's behavior and security are entirely dependent on the integrity and trustworthiness of the `rube.app` service. There is no mechanism to pin a specific version of the Rube MCP service or its tool schemas, meaning changes or compromises to `rube.app` could directly impact the security and functionality of this skill without explicit updates or user intervention. If possible, use a versioned endpoint for the Rube MCP service or implement mechanisms to validate the integrity of the tool schemas and execution environment provided by `rube.app`. Regularly monitor the `rube.app` service for security advisories or changes. Consider implementing a local proxy or caching layer to mitigate direct reliance on the external service for every request.	LLM	SKILL.md:18

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d42eddc6e772ea12.svg)](https://skillshield.io/report/d42eddc6e772ea12)