Security Audit

scrapegraph-ai-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

scrapegraph-ai-automation received a trust score of 85/100, 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 Skill enables broad, unconstrained execution of external toolkit operations.

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

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill enables broad, unconstrained execution of external toolkit operations The skill documentation explicitly guides the user to utilize `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to interact with the `scrapegraph_ai` toolkit. These Rube MCP tools are generic execution mechanisms that allow the LLM to invoke any function or tool exposed by the `scrapegraph_ai` toolkit. Given that `scrapegraph_ai` is designed for web scraping, this skill effectively grants the LLM the ability to perform arbitrary web scraping operations, potentially on sensitive internal or external resources, or other unconstrained actions offered by the toolkit. The skill itself does not define or limit the scope of these underlying tools, leading to excessive permissions for the LLM. Implement more granular access control or specific tool wrappers that limit the LLM's ability to execute arbitrary functions within the `scrapegraph_ai` toolkit. Instead of generic `MULTI_EXECUTE` or `REMOTE_WORKBENCH`, consider defining specific, purpose-built tools for common `scrapegraph_ai` operations with predefined parameters or stricter input validation, thereby reducing the attack surface.	LLM	SKILL.md:50

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/0cb24da1c2842b34.svg)](https://skillshield.io/report/0cb24da1c2842b34)