Security Audit

sympla-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

sympla-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, 1 high, 0 medium, and 0 low severity. Key findings include Generic tool execution via RUBE_REMOTE_WORKBENCH allows broad 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 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

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Generic tool execution via RUBE_REMOTE_WORKBENCH allows broad access The skill documentation suggests using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This construct allows the execution of arbitrary Composio tools. If the underlying Composio tools have broad permissions (e.g., filesystem access, network access to arbitrary domains, access to other sensitive APIs), this skill effectively grants the LLM access to those broad permissions without specific restrictions. An attacker could leverage this to instruct the LLM to execute a malicious Composio tool, potentially leading to unauthorized data access or system manipulation. Restrict the scope of `RUBE_REMOTE_WORKBENCH` to only allow specific, pre-approved Composio tools relevant to Sympla automation, or ensure that the Rube MCP environment enforces strict permission boundaries for tools executed via `run_composio_tool()`. Alternatively, provide more granular tools instead of a generic execution mechanism that can call any Composio tool.	LLM	SKILL.md:59

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/50fd41645637f9a4.svg)](https://skillshield.io/report/50fd41645637f9a4)