Security Audit

peopledatalabs-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

peopledatalabs-automation received a trust score of 84/100, 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 and Excessive Permissions via RUBE_REMOTE_WORKBENCH, Reliance on external Rube MCP introduces supply chain risk.

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

78%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

2 findings

Dynamic Code

2 findings

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Potential Command Injection and Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill exposes `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. A 'remote workbench' typically implies an environment capable of executing code or commands. If `run_composio_tool()` allows the execution of arbitrary Composio tools without strict sandboxing or permission limitations, it could enable an agent to perform command injection, execute unauthorized operations, or leverage excessive permissions granted to the underlying Composio tools. This could lead to unauthorized data access, modification, or system compromise. Clarify the exact capabilities, scope, and sandboxing of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that any executed tools operate within a strictly defined and minimal permission set. Implement robust input validation and execution environment isolation to prevent arbitrary code execution or privilege escalation.	LLM	SKILL.md:80
MEDIUM	Reliance on external Rube MCP introduces supply chain risk The skill explicitly depends on the `rube` MCP, which is an external service hosted at `https://rube.app/mcp`. While not a traditional package dependency, reliance on an external, unversioned endpoint introduces a supply chain risk. A compromise of the `rube.app` service or its infrastructure could lead to malicious tool responses, data exfiltration, or command injection through the tools exposed by the MCP, impacting the security of the agent using this skill. Implement robust monitoring of external dependencies. Consider mechanisms for verifying the integrity and authenticity of responses from the MCP. Document the security posture and auditing practices of the `rube.app` service to assess and mitigate potential risks.	LLM	SKILL.md:15

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/306f1e0c23e3b7b9.svg)](https://skillshield.io/report/306f1e0c23e3b7b9)