Security Audit

humanloop-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

humanloop-automation received a trust score of 83/100, 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 Rube MCP Dependency.

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

78%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad Tool Execution via RUBE_REMOTE_WORKBENCH The skill documents the use of `RUBE_REMOTE_WORKBENCH` for "Bulk ops" with `run_composio_tool()`. This suggests the ability to execute arbitrary Composio tools, potentially across different toolkits, granting very broad and powerful access. A compromised agent leveraging this skill could use `RUBE_REMOTE_WORKBENCH` to perform actions beyond the intended scope of Humanloop automation, leading to privilege escalation or unauthorized operations within the Composio ecosystem. Review the necessity of exposing `RUBE_REMOTE_WORKBENCH` for general use. If broad execution is intended, ensure the agent's environment is highly secured and its access to this tool is strictly controlled. Consider if a more granular tool or a more restricted `run_composio_tool()` interface could be used to limit potential impact.	LLM	SKILL.md:65
MEDIUM	Unpinned Rube MCP Dependency The manifest specifies a dependency on the "rube" MCP (`"mcp": ["rube"]`) without a version constraint. This means the skill could fetch any version of the Rube MCP, including future versions that might introduce vulnerabilities, breaking changes, or malicious code. Explicit version pinning is recommended to ensure deterministic and secure dependency resolution. Specify a precise version or version range for the "rube" MCP dependency in the `requires` field of the manifest (e.g., `"mcp": ["rube@1.2.3"]` or `"mcp": ["rube@^1.0.0"]`) to prevent unexpected or malicious updates.	LLM	Manifest:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/2fe59ec1b4657f94.svg)](https://skillshield.io/report/2fe59ec1b4657f94)