Security Audit

pilvio-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

pilvio-automation received a trust score of 90/100, 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, 1 high, 0 medium, and 0 low severity. Key findings include Use of `RUBE_REMOTE_WORKBENCH` with potentially broad execution capabilities.

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	Use of `RUBE_REMOTE_WORKBENCH` with potentially broad execution capabilities The skill instructs the LLM to use `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' via `run_composio_tool()`. `RUBE_REMOTE_WORKBENCH` is a powerful, general-purpose tool within the Rube ecosystem. Depending on its implementation and the capabilities of `run_composio_tool()`, this could allow the execution of arbitrary Composio tools, potentially extending beyond Pilvio-specific operations, and leading to excessive permissions, data exfiltration, or command injection if not properly sandboxed. The skill's description does not explicitly limit the scope of `run_composio_tool()` to only Pilvio operations, raising concerns about its potential for unintended broad access. Clarify the scope and sandboxing of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` within the context of this skill. If its use is intended to be restricted to Pilvio operations, this should be explicitly stated and enforced. If it is truly a general-purpose execution tool, users should be made aware of the broad permissions it grants and the potential security implications.	LLM	SKILL.md:61

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/365e93e5691ff880.svg)](https://skillshield.io/report/365e93e5691ff880)