Trust Assessment
help received a trust score of 73/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Tool describes broad file reading capability with potential for path traversal.
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 April 1, 2026 (commit c5207c5e). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Tool describes broad file reading capability with potential for path traversal The `SKILL.md` describes a tool named `get_skill_related_file` with the capability to 'Reads any file within a skill directory'. This description implies a broad file access permission. If the underlying implementation of this tool does not strictly sanitize file paths, it could be vulnerable to path traversal attacks (e.g., `../../../../etc/passwd`). An attacker could potentially craft prompts to an LLM to invoke this tool with malicious file paths, leading to unauthorized reading and exfiltration of arbitrary files on the server's filesystem, including sensitive system files or application data. Even if path traversal is prevented, the ability to read 'any file' within a skill directory could be abused by a malicious skill developer to store and retrieve sensitive information. Implement strict path sanitization and sandboxing for the `get_skill_related_file` tool. Ensure that file access is strictly confined to the intended skill's subdirectory and that no path traversal sequences (e.g., `../`) are allowed. Consider if such a broad file-reading capability is truly necessary, or if more granular, restricted access is sufficient for the tool's intended purpose. The tool's documentation should clearly state its security boundaries. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/9ba801899fa89108)
Powered by SkillShield