Trust Assessment
yao received a trust score of 27/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 2 critical, 1 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Unsanitized user input printed to stdout, enabling prompt injection.
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 14, 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 | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/kinmeic/yoebao-yao/yao.py:34 | |
| CRITICAL | Unsanitized user input printed to stdout, enabling prompt injection The skill reads user input from `sys.stdin`, performs minimal string replacements, and then prints this unsanitized input directly to `stdout` as part of its response (`print(f"问题：{question}")`). If the host LLM processes this output, a malicious user could craft their input to include instructions for the host LLM, potentially manipulating its behavior, extracting sensitive information, or causing it to perform unintended actions. Sanitize or escape user input before printing it to `stdout` if the output is intended to be processed by an LLM. Alternatively, ensure that the host LLM is robustly sandboxed and does not interpret skill output as instructions. For example, enclose user-provided text in specific delimiters that the LLM is instructed to ignore for command interpretation. | LLM | yao.py:99 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'call_yao_api'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/kinmeic/yoebao-yao/yao.py:34 |
Scan History
Embed Code
[](https://skillshield.io/report/c427fcd860e32df0)
Powered by SkillShield