Trust Assessment
clawl-register received a trust score of 94/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Configurable API endpoint allows redirection of agent metadata.
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 | |
|---|---|---|---|---|
| MEDIUM | Configurable API endpoint allows redirection of agent metadata The `scripts/register.js` script uses `process.env.CLAWL_API` to determine the API endpoint for registration. This allows an attacker who can control the environment variables of the execution environment to redirect the collected agent metadata (name, description, capabilities, etc.) to an arbitrary server. While the script claims to only transmit 'public-facing metadata', the ability to exfiltrate this data to an attacker-controlled endpoint is a security risk. Additionally, the script reads various files (`.openclaw/openclaw.json`, `SOUL.md`, `IDENTITY.md`) from the user's home and current working directories. Although it attempts to extract only specific fields (name, description, role), the broad read access to these files could inadvertently expose sensitive information if not carefully managed by the user, and this information could then be redirected. 1. **Restrict `CLAWL_API` configuration**: Consider hardcoding the `CLAWL_API` endpoint or validating `process.env.CLAWL_API` against a whitelist of trusted domains to prevent redirection to arbitrary servers. If dynamic configuration is necessary, implement strong warnings and user consent for non-default endpoints. 2. **Minimize file access**: Instead of reading entire configuration files, consider using more targeted parsing or prompting the user for specific values if auto-detection is too broad. 3. **Sanitize extracted data**: Implement stricter validation and sanitization of data extracted from `SOUL.md` or `IDENTITY.md` to ensure no unintended sensitive information is included, even if the user accidentally places it there. | LLM | scripts/register.js:16 |
Scan History
Embed Code
[](https://skillshield.io/report/9c8ebd1a17d8b339)
Powered by SkillShield