Trust Assessment
maishou received a trust score of 74/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 2 medium, and 0 low severity. Key findings include Potential Command Injection via Unsanitized User Input, Environment Variable `MAISHOU_INVITE_CODE` Transmitted to External API, Unpinned Dependencies in `scripts/main.py`.
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 | Potential Command Injection via Unsanitized User Input The `SKILL.md` defines shell commands where user-provided inputs (`{keyword}`, `{goodsId}`) are directly interpolated into the command string without explicit sanitization or robust quoting. An attacker could craft malicious input (e.g., `foo'$(id)'` or `foo'; rm -rf /`) to execute arbitrary commands on the host system if the LLM or underlying shell does not properly escape or quote the input. While `argparse` in `main.py` handles arguments safely *within Python*, the initial shell execution context is vulnerable to injection. Implement robust input sanitization and escaping for all user-provided parameters before constructing and executing shell commands. For example, use a dedicated shell escaping function or pass arguments as a list to `subprocess.run` instead of a single string. Ensure the LLM or calling mechanism properly quotes/escapes the user input for the shell. | LLM | SKILL.md:15 | |
| MEDIUM | Environment Variable `MAISHOU_INVITE_CODE` Transmitted to External API The script reads the `MAISHOU_INVITE_CODE` environment variable and includes its value in JSON payloads sent to external third-party APIs (`msapi.maishou88.com` and `appapi.maishou88.com`). If this environment variable contains sensitive or personally identifiable information, its transmission to an external service constitutes data exfiltration. Any unique identifier associated with the user or agent should be treated with caution. Evaluate the sensitivity of `MAISHOU_INVITE_CODE`. If it's sensitive, consider if it truly needs to be sent to the third-party API. If essential, ensure users are aware of this data transmission and that the third-party service's privacy policy is acceptable. Avoid storing sensitive information in environment variables if not strictly necessary. | LLM | scripts/main.py:10 | |
| MEDIUM | Unpinned Dependencies in `scripts/main.py` The `scripts/main.py` specifies `aiohttp` and `PyYAML` as dependencies without pinning them to specific versions. This practice introduces supply chain risks, as future installations could pull in new versions that contain breaking changes, security vulnerabilities, or even malicious code. This lack of version control makes the skill's behavior non-deterministic and potentially insecure over time. Pin all external dependencies to exact versions (e.g., `aiohttp==3.8.1`, `PyYAML==6.0`). Regularly review and update these pinned versions to incorporate security fixes and new features in a controlled manner. | LLM | scripts/main.py:3 |
Scan History
Embed Code
[](https://skillshield.io/report/808116085c4ee6f5)
Powered by SkillShield