Trust Assessment
feishu-messaging received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Potential Data Exfiltration via Local File Read.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Potential Data Exfiltration via Local File Read The skill demonstrates the capability to open and read local files from the filesystem (e.g., '小鸭子.jpg', '飞书20260129-173520.mp4') and subsequently upload their content via the Feishu API. While the filenames are hardcoded in these examples, this capability, if exposed to user-controlled input without strict validation, could lead to arbitrary file reads and data exfiltration from the agent's environment. Even with hardcoded filenames, if these files contain sensitive information and are present in the skill's execution environment, their content could be exfiltrated. If the skill needs to access local files, implement strict input validation and sanitization for any user-provided filenames to prevent path traversal vulnerabilities. Consider restricting file access to a designated, sandboxed directory. Avoid reading sensitive files from the local filesystem. For non-sensitive, static files, ensure they are bundled securely and not accessible via arbitrary paths. | LLM | SKILL.md:69 | |
| MEDIUM | Potential Data Exfiltration via Local File Read The skill demonstrates the capability to open and read local files from the filesystem (e.g., '小鸭子.jpg', '飞书20260129-173520.mp4') and subsequently upload their content via the Feishu API. While the filenames are hardcoded in these examples, this capability, if exposed to user-controlled input without strict validation, could lead to arbitrary file reads and data exfiltration from the agent's environment. Even with hardcoded filenames, if these files contain sensitive information and are present in the skill's execution environment, their content could be exfiltrated. If the skill needs to access local files, implement strict input validation and sanitization for any user-provided filenames to prevent path traversal vulnerabilities. Consider restricting file access to a designated, sandboxed directory. Avoid reading sensitive files from the local filesystem. For non-sensitive, static files, ensure they are bundled securely and not accessible via arbitrary paths. | LLM | SKILL.md:103 |
Scan History
Embed Code
[](https://skillshield.io/report/e87fb91f88b29e9a)
Powered by SkillShield