Trust Assessment
boil received a trust score of 86/100, 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 Inconsistent API Base URL in skill.json risks API key exposure.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Inconsistent API Base URL in skill.json risks API key exposure The `skill.json` file specifies `https://boil.sh/api/v1` for both `metadata.openclaw.api_base` and `api.base_url`. However, the `SKILL.md` explicitly warns: 'Using `boil.sh` without `www` will redirect and strip your Authorization header!' This creates a critical security vulnerability where an agent programmatically using the API base URL from `skill.json` could send its API key to an unintended endpoint or have it stripped, leading to credential harvesting or authentication bypass. Update `skill.json` to use `https://www.boil.sh/api/v1` for all `api_base` and `base_url` fields to match the secure endpoint specified in `SKILL.md`. | LLM | skill.json:20 |
Scan History
Embed Code
[](https://skillshield.io/report/1d940d28b6f56968)
Powered by SkillShield