Trust Assessment
remote-agent received a trust score of 76/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 1 medium, and 1 low severity. Key findings include Suspicious import: urllib.request, Server-Side Request Forgery (SSRF) via --url argument, Insecure SSL verification option.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Server-Side Request Forgery (SSRF) via --url argument The `REMOTE_AGENT_URL` can be overridden by user input via the `--url` command-line argument. This allows an attacker to make the OpenClaw agent send requests to arbitrary URLs, including internal network resources, cloud metadata endpoints, or other sensitive services. This could lead to data exfiltration, port scanning, or interaction with internal APIs. Remove the `--url` command-line argument. The `REMOTE_AGENT_URL` should only be configurable via environment variables or a secure configuration management system, not directly by user input. If dynamic endpoint selection is required, implement a strict allowlist of permitted URLs. | LLM | scripts/client.py:24 | |
| MEDIUM | Suspicious import: urllib.request Import of 'urllib.request' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/sqsge/clawhub-skill-remote-agent/scripts/client.py:5 | |
| LOW | Insecure SSL verification option The script provides an `--insecure` flag that disables SSL certificate verification. While intended for testing, using this option in a production environment makes the connection vulnerable to man-in-the-middle attacks, potentially leading to data interception or modification. Although a warning is printed to stderr, the LLM consuming the output might not process stderr, thus missing the warning. Remove the `--insecure` flag and associated logic for production deployments. For development/testing, consider using a local proxy or mock server instead of disabling fundamental security protections. If absolutely necessary for specific internal testing, ensure its usage is strictly controlled and never deployed to production. | LLM | scripts/client.py:20 |
Scan History
Embed Code
[](https://skillshield.io/report/52c04aec3f5e8602)
Powered by SkillShield