Trust Assessment
wechat received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Skill requires 'Full Disk Access' for sensitive data.
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 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill requires 'Full Disk Access' for sensitive data The skill's documentation explicitly states that users may need to grant '完全磁盘访问权限' (Full Disk Access) to their terminal on macOS for the underlying script to access the WeChat data directory. While the skill claims to perform 'read-only operations only' and process data locally, granting such broad system-level permissions to any tool, especially one interacting with highly sensitive personal data (chat history, contacts, favorites), introduces a significant security risk if the underlying script (`scripts/wechat.py`) were to be compromised or behave maliciously. This level of access could potentially allow unauthorized reading of any file on the user's system. 1. Thoroughly audit the `scripts/wechat.py` script to confirm it strictly adheres to read-only operations and does not exfiltrate data or perform any unauthorized actions. 2. If possible, explore more granular permission models or sandboxing techniques to limit the scope of access to only the specific WeChat data directories, rather than requiring full disk access. 3. Clearly communicate the implications of granting 'Full Disk Access' to the user, emphasizing the trust required for the underlying script and the potential risks involved. | LLM | SKILL.md:30 |
Scan History
Embed Code
[](https://skillshield.io/report/17e04eb8f80c47cb)
Powered by SkillShield