Security Audit

piggy-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

piggy-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 Unpinned MCP dependency, Broad tool access via Rube MCP.

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	Unpinned MCP dependency The skill depends on the `rube` MCP without specifying a version or hash, relying on `https://rube.app/mcp`. This means the skill will always use the latest version of the MCP, which could change its behavior, introduce vulnerabilities, or become malicious without warning, leading to unexpected or harmful actions. This constitutes a supply chain risk as the integrity and behavior of the dependency are not locked. Specify a version or hash for the `rube` MCP dependency in the manifest if the platform supports it, or implement a mechanism to verify the MCP's integrity and expected behavior before use. Alternatively, consider hosting a pinned version of the MCP.	LLM	SKILL.md:4
MEDIUM	Broad tool access via Rube MCP The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to perform 'Piggy operations' and `run_composio_tool()`. This grants broad access to whatever tools the `rube` MCP exposes for Piggy. While intended for automation, this broad access could allow the LLM to perform highly privileged or destructive actions if the underlying Piggy tools exposed by the Rube MCP have such capabilities and the LLM's usage is not carefully controlled or sandboxed. Implement more granular control over which specific Piggy tools or operations the LLM is allowed to access, or ensure the LLM's execution environment has strict guardrails and human-in-the-loop approval for sensitive or destructive actions when using powerful tools.	LLM	SKILL.md:60

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/3d621dbf8189f8a8.svg)](https://skillshield.io/report/3d621dbf8189f8a8)