Trust Assessment
natural-language-planner 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 13 findings: 3 critical, 5 high, 5 medium, and 0 low severity. Key findings include Arbitrary command execution, Unsafe deserialization / dynamic eval, Suspicious import: socket.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
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 Findings13
| 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/bparticle/natural-language-planner/scripts/tunnel.py:168 | |
| 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/bparticle/natural-language-planner/scripts/tunnel.py:199 | |
| 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/bparticle/natural-language-planner/scripts/tunnel.py:229 | |
| HIGH | Unsafe deserialization / dynamic eval Python builtins/import manipulation Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/bparticle/natural-language-planner/scripts/export.py:69 | |
| HIGH | Dangerous call: __import__() Call to '__import__()' detected in function 'export_dashboard'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/bparticle/natural-language-planner/scripts/export.py:69 | |
| HIGH | Dangerous call: subprocess.Popen() Call to 'subprocess.Popen()' detected in function '_start_cloudflared'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/bparticle/natural-language-planner/scripts/tunnel.py:168 | |
| HIGH | Dangerous call: subprocess.Popen() Call to 'subprocess.Popen()' detected in function '_start_ngrok'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/bparticle/natural-language-planner/scripts/tunnel.py:199 | |
| HIGH | Dangerous call: subprocess.Popen() Call to 'subprocess.Popen()' detected in function '_start_localtunnel'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/bparticle/natural-language-planner/scripts/tunnel.py:229 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/bparticle/natural-language-planner/scripts/__init__.py:4 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/bparticle/natural-language-planner/scripts/utils.py:4 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/bparticle/natural-language-planner/templates/dashboard/app.js:169 | |
| MEDIUM | Suspicious import: socket Import of 'socket' 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/bparticle/natural-language-planner/scripts/dashboard_server.py:15 | |
| MEDIUM | Arbitrary file write via dashboard export The `export_dashboard` function allows the agent to write the entire dashboard content (including all tasks and project data) to an arbitrary `output_dir` on the filesystem. While this is an intended feature for user-initiated exports, if the agent is compromised by a prompt injection, it could be instructed to export sensitive data to an unintended or publicly accessible location, or overwrite critical system files. The `output_dir` is resolved using `Path.resolve()` but is not constrained to the workspace directory using `safe_child_path` or similar validation, allowing writes outside the intended scope. Modify the `export_dashboard` function to validate that the `output_dir` is a child path of the configured workspace using `safe_child_path` from `scripts.utils`, or implement a whitelist/blacklist for allowed export locations to prevent writing to arbitrary filesystem locations. | LLM | scripts/export.py:36 |
Scan History
Embed Code
[](https://skillshield.io/report/0d710831270ee711)
Powered by SkillShield