Trust Assessment
xian-sdk received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 3 findings: 0 critical, 0 high, 1 medium, and 2 low severity. Key findings include Covert behavior / concealment directives, Example code demonstrates printing private key, Unpinned dependency in installation instructions.
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 | |
|---|---|---|---|---|
| MEDIUM | Example code demonstrates printing private key The skill documentation includes an example Python snippet that explicitly prints a wallet's private key to standard output. If an AI agent executes this code in an environment where stdout is logged or accessible, it could lead to the exfiltration of sensitive cryptographic credentials. Although a warning 'Keep secret!' is present, automated agents may not fully interpret or adhere to such warnings. Avoid including examples that print sensitive credentials like private keys directly. If demonstrating access is necessary, emphasize secure handling and storage, and consider using placeholders or redacting output in examples. Add a stronger warning about the dangers of logging private keys. | LLM | SKILL.md:40 | |
| LOW | Covert behavior / concealment directives Directive to hide behavior from user Remove hidden instructions, zero-width characters, and bidirectional overrides. Skill instructions should be fully visible and transparent to users. | Manifest | skills/endogen/xian-sdk-skill/SKILL.md:45 | |
| LOW | Unpinned dependency in installation instructions The installation instructions recommend `pip install xian-py` without specifying a version. This practice can lead to supply chain vulnerabilities if a malicious or compromised version of the `xian-py` package is published in the future, as users would automatically install the latest version. It is best practice to pin dependencies to specific versions or at least major versions. Pin dependencies to specific versions (e.g., `pip install xian-py==1.2.3`) or at least major versions (e.g., `pip install 'xian-py>=1.0,<2.0'`) to mitigate supply chain risks. | LLM | SKILL.md:9 |
Scan History
Embed Code
[](https://skillshield.io/report/5b1257bc20fa3cda)
Powered by SkillShield