Trust Assessment
virustotal security scanner received a trust score of 44/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 6 findings: 0 critical, 3 high, 2 medium, and 1 low severity. Key findings include Suspicious import: requests, Potential data exfiltration: file read + network send, Arbitrary file upload capability.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Static Code Analysis layer scored lowest at 63/100, indicating areas for improvement.
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 Findings6
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential data exfiltration: file read + network send Function 'check_file' reads files and sends data over the network. This may indicate data exfiltration. Review this function to ensure file contents are not being sent to external servers. | Static | skills/aleph8/virustotal-security/vt_client.py:28 | |
| HIGH | Potential data exfiltration: file read + network send Function 'upload_file' reads files and sends data over the network. This may indicate data exfiltration. Review this function to ensure file contents are not being sent to external servers. | Static | skills/aleph8/virustotal-security/vt_client.py:66 | |
| HIGH | Arbitrary file upload capability The `upload_file` function in `vt_client.py` allows the skill to read and upload any file from the agent's filesystem to the VirusTotal API. While the `SKILL.md` contains warnings about user consent, the underlying code provides the capability for data exfiltration if the LLM is prompted to upload sensitive files without proper validation or explicit user confirmation. This poses a significant risk if the LLM's instructions are manipulated or if it acts autonomously without sufficient safeguards. Implement strict validation and explicit user confirmation mechanisms within the LLM's interaction flow before calling `upload_file` with any user-provided or system-derived file path. Consider restricting the directories from which files can be uploaded to only those explicitly approved by the user. | LLM | vt_client.py:40 | |
| 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/aleph8/virustotal-security/vt_client.py:7 | |
| MEDIUM | Potential PII leakage via public comments The `add_comment` function in `vt_client.py` allows the skill to post arbitrary text as a comment to VirusTotal, which is a public threat intelligence service. If the LLM is prompted to include Personally Identifiable Information (PII) or other sensitive data in these comments, it could lead to data exfiltration. Although the `SKILL.md` warns against this, the code itself does not prevent the inclusion of sensitive data. Implement strict sanitization and content filtering for comment text within the LLM's interaction flow. Explicitly warn users about the public nature of comments and advise against including sensitive information. Consider adding a policy to automatically redact common PII patterns before submission. | LLM | vt_client.py:76 | |
| LOW | Unpinned `requests` dependency The `SKILL.md` instructs users to install the `requests` Python library using `pip install requests` without specifying a version. This practice can lead to installing an outdated or potentially vulnerable version if a new vulnerability is discovered in a future release, or if a malicious version is published with the same name (though `requests` is a very well-known package). Specify a pinned version or a version range for the `requests` library (e.g., `pip install requests==2.28.1` or `requests>=2.28,<3.0`) in a `requirements.txt` file or directly in the installation instructions to ensure consistent and secure dependency management. | LLM | SKILL.md:100 |
Scan History
Embed Code
[](https://skillshield.io/report/47618f112eac0995)
Powered by SkillShield