Security Audit

screenshot-fyi-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

screenshot-fyi-automation received a trust score of 82/100, 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 Reliance on external Rube MCP introduces supply chain risk, Dynamic tool execution via Rube MCP allows broad access.

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

Filesystem Write

1 finding

Shell Execution

2 findings

Dynamic Code

2 findings

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Reliance on external Rube MCP introduces supply chain risk The skill explicitly depends on the external Rube MCP service (`https://rube.app/mcp`) for all its functionality, as indicated in the manifest and setup instructions. If the Rube MCP service were compromised or malicious, it could lead to unauthorized actions, data exfiltration, or command injection through the tools it exposes. The skill itself does not mitigate this risk, making it a critical supply chain vulnerability. Implement robust vetting processes for third-party MCPs. Consider sandboxing the execution environment for tools provided by external MCPs. Monitor network traffic for unusual activity and implement strict access controls for the agent's environment.	LLM	SKILL.md:1
MEDIUM	Dynamic tool execution via Rube MCP allows broad access The skill's core workflow involves dynamically discovering and executing tools provided by Rube MCP via `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL`. This pattern allows the agent to execute any tool exposed by Rube for the `screenshot_fyi` toolkit. If Rube MCP were to expose tools with overly broad permissions (e.g., arbitrary file system access, network access beyond the intended scope of Screenshot Fyi, or access to other sensitive systems), the agent could be prompted to execute them, leading to excessive permissions. The skill does not define or restrict the scope of tools it can execute. Implement strict allow-listing for `tool_slug` values that can be executed. Review the schemas returned by `RUBE_SEARCH_TOOLS` to ensure they do not expose sensitive operations. Consider implementing a human-in-the-loop approval process for execution of tools with high-risk permissions.	LLM	SKILL.md:57

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/cf0c5e298cb9ec1d.svg)](https://skillshield.io/report/cf0c5e298cb9ec1d)