Security Audit

affinity-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

affinity-automation received a trust score of 85/100, 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, 0 high, 1 medium, and 0 low severity. Key findings include Broad access via RUBE_REMOTE_WORKBENCH for 'Bulk ops'.

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 20, 2026 (commit 27904475). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

93%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Broad access via RUBE_REMOTE_WORKBENCH for 'Bulk ops' The skill's quick reference section lists `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` as an approach for 'Bulk ops'. The description of `run_composio_tool()` is vague, but the context implies it can execute powerful, potentially arbitrary, Composio operations. If `run_composio_tool()` allows arbitrary code execution or access to a wide range of internal Composio functions without strict validation, a malicious prompt could instruct the LLM to use this tool to perform unauthorized or destructive actions within the connected Affinity account or other Composio-managed systems. This exposes a broad attack surface. Clarify the exact scope and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If `run_composio_tool()` indeed allows arbitrary code execution or highly privileged operations, consider if this skill truly needs to expose such a powerful primitive. Implement strict input validation, authorization checks, and granular permissions within the `run_composio_tool()` implementation to prevent abuse and limit its capabilities to only what is necessary for 'Bulk ops' in Affinity.	Static	SKILL.md:60

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/2c36acb4cc1abf98.svg)](https://skillshield.io/report/2c36acb4cc1abf98)