Security Audit

cardly-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

cardly-automation received a trust score of 80/100, 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 access via Rube MCP, 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 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

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad tool access via Rube MCP The skill `cardly-automation` requires access to the entire `rube` MCP, which includes general-purpose tool execution capabilities like `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` (via `run_composio_tool()`). This grants the skill permissions to execute any tool available through the Rube MCP, potentially beyond the scope of 'Cardly automation' as implied by the skill's name. This broad access could be exploited if the agent is manipulated to call non-Cardly tools. Restrict the `rube` MCP access to only the specific Cardly tools required, if possible, or clearly document the full scope of tools accessible via the `rube` MCP and ensure the agent's usage is constrained to the intended Cardly operations.	LLM	SKILL.md:1
MEDIUM	Unpinned Rube MCP dependency The skill's manifest specifies a dependency on the `rube` MCP without a version constraint. This means the skill will always use the latest version of the `rube` MCP. An unpinned dependency can lead to unexpected behavior, breaking changes, or the introduction of malicious code if the upstream `rube` MCP is compromised or updated with harmful features. Pin the `rube` MCP dependency to a specific, known-good version (e.g., `{"mcp": ["rube@1.2.3"]}`) to ensure stability and prevent unexpected changes from upstream updates.	LLM	manifest.json

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/f07084609c32ea6a.svg)](https://skillshield.io/report/f07084609c32ea6a)