Security Audit

bannerbear-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

bannerbear-automation received a trust score of 82/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Broad Tool Execution via RUBE_REMOTE_WORKBENCH, Unpinned External Dependencies (Rube MCP, Composio Toolkits).

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

78%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Unpinned External Dependencies (Rube MCP, Composio Toolkits) The skill relies on Rube MCP by instructing users to add `https://rube.app/mcp` as an MCP server and implicitly uses Composio's Bannerbear toolkit. Neither the Rube MCP version nor the specific toolkit version is pinned or specified. This introduces a significant supply chain risk, as changes, regressions, or malicious updates to `rube.app/mcp` or the underlying Composio toolkits could directly impact the security and functionality of this skill without the user's explicit consent or awareness. Specify and pin the exact version of Rube MCP and the Composio Bannerbear toolkit that the skill is designed to work with. If direct version pinning isn't possible for the MCP endpoint, consider adding checksums or other integrity checks for the tools retrieved from it to ensure their authenticity and immutability.	LLM	SKILL.md:20
MEDIUM	Broad Tool Execution via RUBE_REMOTE_WORKBENCH The skill exposes the `RUBE_REMOTE_WORKBENCH` tool, specifically mentioning `run_composio_tool()` for 'Bulk ops'. This capability allows for the execution of arbitrary functions within the Composio toolkit ecosystem. While intended for flexibility, it grants the LLM broad permissions to invoke any available `composio_tool` function without specific constraints defined within the skill itself. A malicious prompt could leverage this to perform unintended actions beyond the scope of Bannerbear automation, potentially leading to excessive permissions being exercised. If possible, restrict the `RUBE_REMOTE_WORKBENCH` tool to only specific, pre-approved Bannerbear operations or functions, rather than allowing arbitrary `run_composio_tool()` calls. Alternatively, ensure the underlying `run_composio_tool()` implementation has robust access controls and logging to mitigate abuse.	LLM	SKILL.md:68

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/2507de50a77da04f.svg)](https://skillshield.io/report/2507de50a77da04f)