Security Audit

fireberry-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

fireberry-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 Skill grants broad control over Fireberry via Rube MCP tools.

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

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill grants broad control over Fireberry via Rube MCP tools The skill instructs the LLM agent to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to interact with the Fireberry system via Composio's Rube MCP. These tools allow the agent to perform any operation exposed by the `fireberry` toolkit, which could include sensitive actions like data manipulation, user management, or configuration changes within Fireberry. The skill's documentation does not define or restrict the scope of these operations, effectively granting the agent excessive permissions to the connected Fireberry account. An attacker could potentially prompt the agent to perform unauthorized or destructive actions. Restrict the scope of the `fireberry` toolkit within Composio to only necessary operations. If broad access is required, implement strict human-in-the-loop approval for sensitive actions or use fine-grained access control within Fireberry. For the skill itself, consider providing more specific tools or use cases instead of a generic `MULTI_EXECUTE_TOOL` if possible, or clearly document the potential impact of the broad permissions.	LLM	SKILL.md:60

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d50f0920b2517cd6.svg)](https://skillshield.io/report/d50f0920b2517cd6)