Security Audit

claude-dev-suite/claude-dev-suite:skills/api-design/openapi

github.com/claude-dev-suite/claude-dev-suite

AI SkillCommit 8c8434ef25f0

TRUSTED

Scanned 14 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

claude-dev-suite/claude-dev-suite:skills/api-design/openapi 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 2 findings: 0 critical, 0 high, 1 medium, and 1 low severity. Key findings include Excessive Write/Edit Permissions, Broad File System Reconnaissance Permissions.

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 March 16, 2026 (commit 8c8434ef). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

100%

Static Code Analysis

91%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

2 findings

Dynamic Code

1 finding

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
MEDIUM	Excessive Write/Edit Permissions The skill declares 'Write' and 'Edit' permissions, which are overly broad. While an OpenAPI skill may require modifying specification files, these permissions grant the agent the ability to write to or edit any file within the repository's scope. This could be exploited by a malicious prompt to modify sensitive configuration files, inject malicious code, or delete critical data, leading to data integrity issues or further compromise. Restrict write/edit permissions to specific file types (e.g., `.yaml`, `.json`) or directories relevant to OpenAPI specifications. If fine-grained control is not possible, ensure the agent's execution environment is heavily sandboxed to prevent abuse of these broad permissions.	Static	SKILL.md:1
LOW	Broad File System Reconnaissance Permissions The skill declares 'Glob' and 'Grep' permissions. While useful for finding OpenAPI specification files, these permissions allow the agent to perform broad file system reconnaissance across the entire repository. A malicious prompt could leverage these tools to discover sensitive files, credentials, or other valuable information that could then be exfiltrated if combined with other capabilities (e.g., if the agent has network access or can write to external locations). Consider if 'Glob' and 'Grep' are strictly necessary for the core function of the skill, or if their scope can be limited to specific directories or file patterns. Implement strict sandboxing and monitoring of file system access by the agent.	Static	SKILL.md:1

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/f02aebdee16616f1.svg)](https://skillshield.io/report/f02aebdee16616f1)