Trust Assessment
apple-mail-moltbot-skill 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 12 findings: 7 critical, 4 high, 1 medium, and 0 low severity. Key findings include Arbitrary command execution, Missing required field: name, Dangerous call: subprocess.run().
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 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings12
| 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/latisen/apple-mail-moltbot-skill/scripts/get_message_content.py:23 | |
| 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/latisen/apple-mail-moltbot-skill/scripts/get_messages.py:26 | |
| 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/latisen/apple-mail-moltbot-skill/scripts/list_accounts.py:20 | |
| 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/latisen/apple-mail-moltbot-skill/scripts/list_mailboxes.py:23 | |
| CRITICAL | Arbitrary AppleScript/Shell Command Injection via message_id The `message_id` argument, taken directly from user input (`sys.argv[1]`), is unsafely interpolated into an AppleScript string. An attacker can inject arbitrary AppleScript commands, including `do shell script`, leading to arbitrary shell command execution on the host system. For example, providing `123456" & do shell script "rm -rf /" & "` as `message_id` could execute a shell command. Sanitize `message_id` by properly escaping any special characters (e.g., double quotes) before embedding it into the AppleScript string. If `message_id` is expected to be an integer, cast it to an integer to prevent string-based injection. Example: `set msg to first message whose id is "{message_id.replace('"', '\"')}"` | LLM | scripts/get_message_content.py:30 | |
| CRITICAL | Arbitrary AppleScript/Shell Command Injection via account_name and mailbox_name The `account_name` and `mailbox_name` arguments, taken directly from user input (`argparse`), are unsafely interpolated into an AppleScript string. An attacker can inject arbitrary AppleScript commands, including `do shell script`, leading to arbitrary shell command execution on the host system. For example, providing `MyAccount" & do shell script "echo PWNED" & "` as `account_name` could execute a shell command. Sanitize `account_name` and `mailbox_name` by properly escaping any special characters (e.g., double quotes) before embedding them into the AppleScript string. Example: `set acc to account "{account_name.replace('"', '\"')}"` | LLM | scripts/get_messages.py:30 | |
| CRITICAL | Arbitrary AppleScript/Shell Command Injection via account_name The `account_name` argument, taken directly from user input (`sys.argv[1]`), is unsafely interpolated into an AppleScript string. An attacker can inject arbitrary AppleScript commands, including `do shell script`, leading to arbitrary shell command execution on the host system. For example, providing `MyAccount" & do shell script "echo PWNED" & "` as `account_name` could execute a shell command. Sanitize `account_name` by properly escaping any special characters (e.g., double quotes) before embedding it into the AppleScript string. Example: `set acc to account "{account_name.replace('"', '\"')}"` | LLM | scripts/list_mailboxes.py:30 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_osascript'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/latisen/apple-mail-moltbot-skill/scripts/get_message_content.py:23 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_osascript'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/latisen/apple-mail-moltbot-skill/scripts/get_messages.py:26 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_osascript'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/latisen/apple-mail-moltbot-skill/scripts/list_accounts.py:20 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_osascript'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/latisen/apple-mail-moltbot-skill/scripts/list_mailboxes.py:23 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/latisen/apple-mail-moltbot-skill/SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/c2e7eba809e21a2e)
Powered by SkillShield