Security Audit

esp32-weather

github.com/openclaw/skills

AI SkillCommit 13146e6a3d46

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

esp32-weather received a trust score of 56/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Server-Side Request Forgery (SSRF) via user-controlled IP address.

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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.

Layer Breakdown

Manifest Analysis

70%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Network Access

2 findings

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
CRITICAL	Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains.	Manifest	skills/manisaigaddam/weather-esp32/SKILL.md:64
HIGH	Server-Side Request Forgery (SSRF) via user-controlled IP address The skill instructs the LLM to make HTTP GET requests to an IP address (`http://{ESP32_IP}/reading`, `http://{ESP32_IP}/health`) that is explicitly set by the user via the command 'Set ESP32 IP to X.X.X.X'. This allows an attacker to provide an arbitrary IP address, potentially an internal network address or a sensitive external host, leading to Server-Side Request Forgery (SSRF). This could be exploited to scan internal networks, access internal services (e.g., cloud metadata services), or interact with unintended external resources. Implement strict validation and sanitization of the user-provided IP address. Only allow specific, whitelisted IP ranges (e.g., private network ranges if the ESP32 is expected to be local) or use a whitelist of allowed hostnames/IPs. Ensure the LLM's HTTP client is configured to prevent requests to private IP ranges and sensitive metadata endpoints (e.g., 169.254.169.254).	LLM	SKILL.md:35

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e51ea100a823aac6.svg)](https://skillshield.io/report/e51ea100a823aac6)