Security Audit

needle-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

needle-automation received a trust score of 78/100, 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 Unpinned External MCP Dependency, Broad Tool Access via Rube MCP.

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

78%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

2 findings

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Unpinned External MCP Dependency The skill explicitly instructs the LLM to connect to an external Managed Control Plane (MCP) at `https://rube.app/mcp`. There is no version pinning or integrity verification mechanism for this external service. If the `rube.app` domain or its hosted MCP were compromised or became malicious, the LLM using this skill would be directed to an untrusted endpoint, potentially leading to arbitrary code execution, data exfiltration, or other severe security breaches through the tools it provides. Implement version pinning or cryptographic integrity checks for external MCP dependencies. Clearly document the risks associated with connecting to unverified external services and advise users to only connect to trusted and secured endpoints. Consider hosting critical MCPs internally or through trusted, audited providers.	Static	SKILL.md:15
MEDIUM	Broad Tool Access via Rube MCP The skill encourages the use of `RUBE_MULTI_EXECUTE_TOOL` and explicitly mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. These tools, particularly `RUBE_REMOTE_WORKBENCH`, grant the LLM broad capabilities to execute arbitrary Composio tools within the Rube ecosystem. While this is the intended functionality of the skill, it represents a significant increase in the LLM's operational scope. A malicious prompt or a compromised LLM could potentially abuse this broad access to perform unauthorized actions through any available Composio tool. Users should be made aware of the extensive permissions granted by this skill. Implement strict access controls and monitoring for LLM interactions with `RUBE_REMOTE_WORKBENCH`. Consider restricting the set of tools accessible via `run_composio_tool()` or requiring explicit human approval for sensitive operations. Ensure that the underlying Composio tools themselves adhere to the principle of least privilege.	Static	SKILL.md:70

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/3ca1c82cb16221eb.svg)](https://skillshield.io/report/3ca1c82cb16221eb)