Trust Assessment
zentao received a trust score of 80/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Unpinned dependency in installation instructions, Sensitive credentials exposed in command line arguments.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned dependency in installation instructions The skill instructs users to install the `@leeguoo/zentao-mcp` package globally using `pnpm i -g @leeguoo/zentao-mcp`. No specific version is pinned, meaning that any future malicious update to this package could be automatically installed, compromising the system. This creates a significant supply chain risk. Pin the dependency to a specific, known-good version (e.g., `pnpm i -g @leeguoo/zentao-mcp@1.2.3`). Regularly audit the chosen version for vulnerabilities. | LLM | SKILL.md:20 | |
| MEDIUM | Sensitive credentials exposed in command line arguments The `zentao login` command requires the user's password to be passed directly as a command-line argument (`--zentao-password`). This practice can expose sensitive credentials in shell history files, process lists (e.g., `ps aux`), and potentially in LLM interaction logs if the LLM is instructed to execute this command. While the skill itself doesn't exfiltrate, it guides the user into an insecure credential handling pattern. Recommend using environment variables, secure input prompts (e.g., `read -s`), or a configuration file for sensitive credentials instead of command-line arguments. If command-line is unavoidable, advise users about the risks and how to clear history. | LLM | SKILL.md:33 |
Scan History
Embed Code
[](https://skillshield.io/report/a9b74fdff039bf71)
Powered by SkillShield