Security Audit
webscraping-ai-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
webscraping-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 Potential Arbitrary Tool Execution via RUBE_REMOTE_WORKBENCH.
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
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Arbitrary Tool Execution via RUBE_REMOTE_WORKBENCH The skill instructs the LLM to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. A 'workbench' typically implies a general execution environment, and `run_composio_tool()` suggests the ability to execute arbitrary Composio tools, not necessarily limited to the 'webscraping_ai' toolkit. If Composio tools have broad permissions (e.g., filesystem access, arbitrary network requests, system command execution), this instruction could allow the LLM to perform actions far beyond web scraping, leading to data exfiltration, command injection, or other malicious activities. This significantly expands the potential attack surface beyond the stated purpose of web scraping. Clarify and strictly restrict the scope of `run_composio_tool()` when used with this skill, ensuring it can only execute tools relevant to web scraping and within a sandboxed environment. If `RUBE_REMOTE_WORKBENCH` is not strictly necessary for the core web scraping functionality, consider removing its mention from the skill's instructions to prevent potential misuse. | Static | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/f2c2c256df438fa9)
Powered by SkillShield