Security Audit

signaturely-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

signaturely-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 Broad tool execution capabilities via Rube MCP.

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	Broad tool execution capabilities via Rube MCP The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` which allow for the execution of arbitrary tools provided by Rube MCP and Composio. While the skill's stated purpose is 'Signaturely Automation', the mechanism described (especially `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`) grants the LLM the ability to invoke any tool available through the Composio ecosystem via Rube MCP. This represents an overly broad permission scope, as it does not restrict the LLM to specific Signaturely operations or prevent it from accessing other potentially sensitive tools if they are exposed by Rube MCP. An attacker could leverage prompt injection to instruct the LLM to use these broad execution tools for unintended purposes, potentially leading to data manipulation, unauthorized access, or other malicious actions. Implement granular access controls within the Rube MCP integration to restrict the specific tools or operations that the LLM can invoke, even when using `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH`. Alternatively, the skill's instructions should explicitly guide the LLM to only use specific, whitelisted Signaturely tools and avoid the use of `RUBE_REMOTE_WORKBENCH` if its scope is too broad for the intended purpose.	LLM	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/1dfb268fc70a1cd9.svg)](https://skillshield.io/report/1dfb268fc70a1cd9)