Security Audit

anchor-browser-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

anchor-browser-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 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Potential Command Injection via RUBE_REMOTE_WORKBENCH, Excessive Permissions via RUBE_MULTI_EXECUTE_TOOL.

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

1 finding

Filesystem Write

2 findings

Shell Execution

2 findings

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via RUBE_REMOTE_WORKBENCH The skill instructs the LLM to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The `run_composio_tool()` function implies a generic execution capability. If this function is not strictly sandboxed or allows arbitrary command execution, it presents a direct path for command injection, enabling an attacker to execute malicious code on the host system or within the tool's environment. Ensure `run_composio_tool()` executed via `RUBE_REMOTE_WORKBENCH` is strictly sandboxed, operates with the principle of least privilege, and has no access to arbitrary shell commands or sensitive file system paths. Implement strict input validation and allow-listing for tool arguments.	LLM	SKILL.md:87
MEDIUM	Excessive Permissions via RUBE_MULTI_EXECUTE_TOOL The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` to execute any tool discovered via `RUBE_SEARCH_TOOLS`. This mechanism grants the LLM the ability to trigger any 'Anchor Browser' tool. If these underlying tools possess broad permissions (e.g., arbitrary file system access, network requests to untrusted domains, or access to sensitive APIs), the LLM could be prompted to perform actions with excessive privileges, potentially leading to data exfiltration or unauthorized system modifications. Ensure all tools discoverable via `RUBE_SEARCH_TOOLS` and executable via `RUBE_MULTI_EXECUTE_TOOL` operate with the principle of least privilege. Implement granular access controls for each tool and its operations, restricting their capabilities to only what is strictly necessary for their intended function.	LLM	SKILL.md:65

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e9dc8e2edee79a5f.svg)](https://skillshield.io/report/e9dc8e2edee79a5f)