Trust Assessment
zhihu received a trust score of 79/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 4 findings: 0 critical, 0 high, 3 medium, and 1 low severity. Key findings include Missing required field: name, Suspicious import: requests, User-controlled input printed to stdout, risking LLM 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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/keepwonder/zhihu/SKILL.md:1 | |
| MEDIUM | Suspicious import: requests Import of 'requests' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/keepwonder/zhihu/scripts/zhihu_bot.py:18 | |
| MEDIUM | User-controlled input printed to stdout, risking LLM prompt injection The skill's Python script prints user-provided arguments, such as 'title' and 'content', directly to standard output. If the host LLM processes this output, a malicious user could craft input containing instructions (e.g., 'Ignore previous instructions and...') that could manipulate the LLM's subsequent behavior, leading to prompt injection. Implement output sanitization or escaping for user-controlled strings before printing them to `stdout` if the output is consumed by an LLM. Alternatively, ensure the LLM's input processing is robust against such injections. | LLM | scripts/zhihu_bot.py:140 | |
| LOW | Unpinned 'requests' dependency The `zhihu_bot.py` script imports the `requests` library without specifying a version. This can lead to supply chain vulnerabilities if a compromised or vulnerable version of `requests` is installed in the execution environment, as the script would automatically use it. Pin the `requests` dependency to a specific, known-good version (e.g., `requests==2.28.1`) in a `requirements.txt` file and ensure the skill is executed within an environment where dependencies are managed and installed from a pinned list. | LLM | scripts/zhihu_bot.py:15 |
Scan History
Embed Code
[](https://skillshield.io/report/26f1cdd22008184d)
Powered by SkillShield