Trust Assessment
jina-reader received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Suspicious import: requests, Arbitrary File Write via Output Argument.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary File Write via Output Argument The `jina-reader.py` script allows users to specify an arbitrary file path for output using the `-o` or `--output` argument. The `Path(args.output).write_text()` function is then called with this user-controlled path without any sanitization or restriction. This means an attacker could provide a sensitive system file path (e.g., `/etc/passwd`, `/root/.ssh/authorized_keys`, `/var/www/html/malicious.php`) to overwrite or create files with content fetched from the Jina Reader API. This could lead to privilege escalation, denial of service, or other system compromises depending on the execution context and file system permissions of the AI agent. Restrict the `--output` argument to write only within a designated, non-sensitive directory (e.g., a temporary directory or a specific output folder). Implement path sanitization to prevent directory traversal (e.g., `../`) and ensure the target path is not an absolute system path. Alternatively, if writing to arbitrary paths is a required feature, ensure the AI agent executing this skill operates with extremely limited file system write permissions. | LLM | scripts/jina-reader.py:120 | |
| 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/smile-xuc/haibo-jina-reader/scripts/jina-reader.py:14 |
Scan History
Embed Code
[](https://skillshield.io/report/138912e22c883a78)
Powered by SkillShield