Security Audit

tpscheck-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

tpscheck-automation received a trust score of 89/100, 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, 0 high, 2 medium, and 0 low severity. Key findings include Unpinned dependency on external MCP, Potential for excessive permissions through generic tool execution.

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

86%

Behavioral Risk Signals

Network Access

2 findings

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
MEDIUM	Unpinned dependency on external MCP The skill manifest declares a dependency on the 'rube' MCP without specifying a version. This means the skill will always use the latest version of the 'rube' MCP, which could introduce breaking changes, vulnerabilities, or malicious behavior if the MCP provider's integrity is compromised. Without version pinning, there's no guarantee of consistent or secure behavior over time. If possible, specify a version or a version range for the 'rube' MCP dependency in the manifest to ensure stability and security. Regularly review and update the dependency to mitigate supply chain risks.	LLM	SKILL.md
MEDIUM	Potential for excessive permissions through generic tool execution The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` (specifically `run_composio_tool()`). These mechanisms allow for dynamic execution of tools discovered via `RUBE_SEARCH_TOOLS`. If the Rube MCP system provides access to tools with broad or sensitive capabilities (e.g., file system access, network access to internal resources, or management of other services), this skill provides a direct interface for the LLM to invoke those tools. The skill itself does not enforce granular restrictions on which tools can be executed beyond what the Rube MCP makes available, potentially leading to excessive permissions if the underlying tools are misused or compromised. Implement stricter controls within the Rube MCP system or the LLM's tool invocation layer to limit the scope of tools that can be executed by this skill. For example, whitelist specific `tool_slug` values or restrict `run_composio_tool()` to a predefined set of safe operations relevant only to Tpscheck tasks.	LLM	SKILL.md:80

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/f5e711c0c19668a2.svg)](https://skillshield.io/report/f5e711c0c19668a2)