Security Audit

workable-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

workable-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, 1 high, 0 medium, and 0 low severity. Key findings include Broad access to sensitive Workable data.

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

85%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad access to sensitive Workable data The skill grants the LLM broad capabilities to interact with Workable via `RUBE_MULTI_EXECUTE_TOOL` and the Composio Workable toolkit. Workable is an Applicant Tracking System (ATS) that typically contains highly sensitive Personally Identifiable Information (PII) such as candidate resumes, contact details, and employment history. The skill does not define granular permissions or scope limitations for the LLM's actions, allowing it to potentially perform any operation (read, write, delete) on this sensitive data based on user prompts. This poses a significant risk of unauthorized data access, modification, or exfiltration if the LLM is compromised or misused. Implement granular access controls or scope limitations for the Workable toolkit. If possible, restrict the types of Workable operations the LLM can perform (e.g., read-only access for certain data, or specific actions only). Require explicit user confirmation for sensitive operations. Ensure that the `RUBE_SEARCH_TOOLS` output can be filtered or constrained to only expose necessary functionalities.	LLM	SKILL.md:50

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/9e077052f15d4d09.svg)](https://skillshield.io/report/9e077052f15d4d09)