Security Audit

agiled-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

agiled-automation received a trust score of 88/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Excessive Permissions via Generic Tool Access.

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

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Excessive Permissions via Generic Tool Access The skill documentation includes `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` in its 'Quick Reference'. While the skill's manifest and description (e.g., 'Automate Agiled tasks via Rube MCP') imply a focus on 'Agiled operations', the `run_composio_tool()` function is generic. If the underlying Rube MCP and Composio platform do not strictly enforce that `run_composio_tool()` can only invoke tools from the 'agiled' toolkit within the context of this skill, an LLM could potentially use this tool to access or manipulate data via other connected Composio toolkits, leading to excessive permissions beyond the intended scope of 'Agiled automation'. Clarify the scope of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` in the skill documentation. Explicitly state if `run_composio_tool()` is restricted to only 'agiled' toolkit operations when used within this skill. If it's not intended for general use, consider removing it from the quick reference or providing a more specific example that demonstrates its use only for Agiled-related bulk operations.	LLM	SKILL.md:94

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/dccf27f4f566eaae.svg)](https://skillshield.io/report/dccf27f4f566eaae)