Security Audit

convolo-ai-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

convolo-ai-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 Skill leverages generic tool execution with broad scope.

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

93%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Skill leverages generic tool execution with broad scope The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`, which are generic tools provided by Rube MCP. These tools allow the execution of any tool available through the MCP, identified by `tool_slug` or `run_composio_tool()`. While the skill's manifest and description indicate an intent to automate 'Convolo AI operations', the underlying execution mechanisms grant broad permissions to execute arbitrary tools within the Rube MCP ecosystem. If the LLM's instructions are compromised (e.g., via prompt injection), it could be coerced into executing tools outside the intended Convolo AI scope, potentially leading to unintended actions or access to other systems connected to Rube MCP. Implement strict input validation and sandboxing for LLM-generated tool calls. Ensure that the Rube MCP itself enforces granular access control, limiting the LLM's ability to execute tools only to those explicitly required for Convolo AI operations, even when generic execution tools are used. Consider adding a wrapper or guardrail that validates `tool_slug` against an allow-list of Convolo AI tools before execution.	LLM	SKILL.md:55

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/57d686902b8ace62.svg)](https://skillshield.io/report/57d686902b8ace62)