Security Audit

twocaptcha-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned 6 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

twocaptcha-automation received a trust score of 95/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.

SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Broad Rube MCP tool access grants excessive 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

93%

Behavioral Risk Signals

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Broad Rube MCP tool access grants excessive permissions The skill's manifest declares a dependency on the Rube MCP (`mcp: ["rube"]`). This grants the agent access to a suite of powerful, generic tools provided by Rube, including `RUBE_MANAGE_CONNECTIONS`, `RUBE_MULTI_EXECUTE_TOOL`, and `RUBE_REMOTE_WORKBENCH`. While the skill's documentation guides the agent to use these tools specifically for Twocaptcha operations (e.g., `RUBE_MANAGE_CONNECTIONS` with `toolkit: "twocaptcha"`), the underlying tools themselves are not inherently scoped. An agent granted access to the Rube MCP via this skill could potentially be prompted to manage connections for other toolkits or execute arbitrary tools available through Rube, leading to unintended actions on other connected services beyond the scope of Twocaptcha. If possible, implement fine-grained access control for Rube MCP tools to restrict `RUBE_MANAGE_CONNECTIONS` to only the `twocaptcha` toolkit and `RUBE_MULTI_EXECUTE_TOOL` to only Twocaptcha-related tool slugs. Alternatively, ensure the agent's overall permissions and prompt engineering are strictly scoped to prevent misuse of these powerful, generic tools.	LLM	Manifest

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d01d4679ec7fbed1.svg)](https://skillshield.io/report/d01d4679ec7fbed1)