Trust Assessment
set-reminder received a trust score of 43/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 1 critical, 2 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Dangerous call: subprocess.run(), Potential Command Injection via `subprocess` with user-controlled arguments.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
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 Findings3
| 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/onionrings29/set-reminder/scripts/set_reminder.py:386 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_cron_command'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/onionrings29/set-reminder/scripts/set_reminder.py:386 | |
| HIGH | Potential Command Injection via `subprocess` with user-controlled arguments The skill's documentation states it "Creates cron job via `openclaw cron add`", and the `scripts/set_reminder.py` file imports the `subprocess` module. User-provided arguments such as `--message`, `--at`, `--every`, and `--cron` are passed to this external command. If these inputs are not properly sanitized and escaped when constructing the command for `subprocess.run()`, an attacker could inject arbitrary shell commands. The `sanitize_name` function is present (though truncated), indicating an awareness of input sanitization needs, but its full implementation and application to all relevant inputs cannot be verified due to the truncated code. Ensure all user-provided arguments passed to `subprocess.run()` are provided as a list of strings (e.g., `["command", "arg1", "arg2"]`) and *never* use `shell=True` with unsanitized user input. If `shell=True` is absolutely necessary, use `shlex.quote()` to properly escape all user-provided arguments. Verify that the `sanitize_name` function (or equivalent sanitization) is robust and applied to all user-controlled inputs before they are used in external command execution. | LLM | scripts/set_reminder.py:25 |
Scan History
Embed Code
[](https://skillshield.io/report/933179ea074053c6)
Powered by SkillShield