Security Audit

jobnimbus-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

jobnimbus-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 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Potential Command Injection / Excessive Permissions via RUBE_REMOTE_WORKBENCH, Agent instructed to follow external authentication link for credential setup.

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

2 findings

Dynamic Code

1 finding

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Potential Command Injection / Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill instructs the agent to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'workbench' often implies an environment capable of executing arbitrary code or commands. If `run_composio_tool()` allows for execution of unvalidated or arbitrary commands, it could lead to command injection. Furthermore, a 'remote workbench' inherently suggests broad permissions within that environment, potentially allowing access to resources beyond the intended scope, leading to excessive permissions. Clarify the exact capabilities and security implications of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that `run_composio_tool()` is sandboxed and only allows execution of pre-defined, safe operations, or that the agent is explicitly warned about its power and instructed on how to validate inputs and manage permissions.	LLM	SKILL.md:80
MEDIUM	Agent instructed to follow external authentication link for credential setup The skill instructs the agent to 'follow the returned auth link to complete setup' if the Jobnimbus connection is not active. This process involves interacting with an external authentication flow, which could expose sensitive credentials (e.g., OAuth tokens, API keys) to the agent. A malicious or compromised auth link, or improper handling of the authentication flow by the agent, could lead to credential harvesting or unauthorized access. While the skill itself doesn't harvest, it directs the agent to a sensitive interaction point. Provide explicit instructions to the agent on how to securely handle external authentication links, validate their authenticity, and manage any returned credentials (e.g., store them securely, do not log them, do not expose them to untrusted contexts). Emphasize that the agent should only proceed with trusted and verified authentication flows.	LLM	SKILL.md:19

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/ad1e4de2c4e5e9b7.svg)](https://skillshield.io/report/ad1e4de2c4e5e9b7)