Security Audit

anchor-browser-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

anchor-browser-automation received a trust score of 86/100, 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 Dynamic Tool Discovery and Execution Grants Broad Permissions.

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

85%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Dynamic Tool Discovery and Execution Grants Broad Permissions The skill instructs the LLM to use `RUBE_SEARCH_TOOLS` to dynamically discover available Anchor Browser operations and then `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH` to execute them. This pattern grants the LLM the ability to perform any action exposed by the Anchor Browser toolkit via Rube MCP, without explicit prior approval for each specific tool. This broad, dynamic execution capability could lead to unintended or malicious actions if the LLM is compromised or misinterprets user intent. The `RUBE_REMOTE_WORKBENCH` further enables 'Bulk ops' and general `run_composio_tool()` execution, increasing the scope of potential actions. Implement stricter access controls or a human-in-the-loop approval process for sensitive operations discovered via `RUBE_SEARCH_TOOLS`. Consider limiting the scope of tools exposed to the LLM or requiring explicit user confirmation for high-impact actions. For `RUBE_REMOTE_WORKBENCH`, ensure its capabilities are strictly confined and monitored.	LLM	SKILL.md:28

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/78419164570f3509.svg)](https://skillshield.io/report/78419164570f3509)