Trust Assessment
threads received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 4 findings: 3 critical, 0 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Python file could not be statically analyzed, Arbitrary Local File Upload to External Service.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, 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 Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/ruslanlanket/threads/scripts/threads_cli.py:28 | |
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/ruslanlanket/threads/scripts/threads_cli.py:43 | |
| CRITICAL | Arbitrary Local File Upload to External Service The skill allows users to specify an arbitrary local file path via the `--image` argument. This file is then uploaded directly to an external, temporary hosting service (catbox.moe) without any path validation or sandboxing. This enables a malicious actor to exfiltrate any file accessible to the agent's execution environment, such as sensitive configuration files, credentials (e.g., `/etc/passwd`, `~/.ssh/id_rsa`, API keys), or other private data. Implement strict validation for file paths to ensure they are within an allowed, sandboxed directory. Alternatively, remove the local file upload feature if not strictly necessary. If local file upload is required, ensure files are processed securely within the agent's environment and not directly uploaded to third-party services without explicit user confirmation and robust security controls. | LLM | scripts/threads_cli.py:34 | |
| MEDIUM | Python file could not be statically analyzed SyntaxError: expected an indented block after 'if' statement on line 51 (line 53) | Static | skills/ruslanlanket/threads/scripts/threads_cli.py:53 |
Scan History
Embed Code
[](https://skillshield.io/report/4e5169b9eb15fd78)
Powered by SkillShield