Security Audit

draftable-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

draftable-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 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Vaguely defined powerful tool access.

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

93%

Behavioral Risk Signals

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Vaguely defined powerful tool access The skill instructs the LLM to use `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. The capabilities of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` are not clearly defined, but 'Bulk ops' suggests a broad and potentially powerful scope of operations. This could lead to excessive permissions if the underlying tool allows for highly privileged or destructive actions without granular control, or if it can be manipulated to execute arbitrary commands or scripts within the Composio environment. The lack of specific details makes it difficult to assess the full extent of the risk. Provide a more detailed description of the `RUBE_REMOTE_WORKBENCH` tool and the `run_composio_tool()` function, including their exact capabilities, limitations, and any security implications. If `run_composio_tool()` allows for scripting or arbitrary command execution, ensure robust input validation and sandboxing are in place, and explicitly document these safeguards. Consider if such a powerful tool is strictly necessary for the skill's intended purpose, or if more granular tools could be used.	LLM	SKILL.md:70

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/9d0d1e0e02dea7ef.svg)](https://skillshield.io/report/9d0d1e0e02dea7ef)