Trust Assessment
blog-to-kindle 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 6 findings: 3 critical, 3 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Sensitive path access: AI agent config.
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 Findings6
| 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/ainekomacx/blog-to-kindle/scripts/compile_epub.py:90 | |
| 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/ainekomacx/blog-to-kindle/scripts/send_to_kindle.py:26 | |
| CRITICAL | AppleScript injection via user input The `scripts/send_to_kindle.py` script constructs an AppleScript command string using user-provided values for `file_path`, `kindle_email`, and `subject`. These values are directly interpolated into the AppleScript string without proper escaping. An attacker can inject arbitrary AppleScript commands by including double quotes (`"`) and other AppleScript syntax in their input. This could lead to arbitrary code execution on the user's macOS system, allowing for data exfiltration, file manipulation, or other malicious actions. Properly escape all user-provided input before embedding it into the AppleScript string. For example, replace all double quotes (`"`) with `\"` or use a dedicated AppleScript escaping function. Alternatively, consider using a more robust method for interacting with Mail.app that doesn't involve direct string interpolation of user input into an executable script. | LLM | scripts/send_to_kindle.py:20 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'main'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/ainekomacx/blog-to-kindle/scripts/compile_epub.py:90 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'send_via_mail_app'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/ainekomacx/blog-to-kindle/scripts/send_to_kindle.py:26 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/ainekomacx/blog-to-kindle/SKILL.md:68 |
Scan History
Embed Code
[](https://skillshield.io/report/4ed6e0ce56cba367)
Powered by SkillShield