Trust Assessment
quick-reminders received a trust score of 70/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Unsafe shell command construction in nohup-reminder.sh.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Unsafe shell command construction in nohup-reminder.sh The `cmd_add` function constructs a `nohup` command string by directly interpolating user-controlled variables (`$REMINDER_TARGET`, `$channel`, `$text`) into a `bash -c` command without proper shell escaping. An attacker can inject arbitrary shell commands by crafting malicious values for these parameters, leading to remote code execution within the context of the skill's execution environment. Properly quote and escape all user-provided arguments before interpolating them into the `bash -c` string. For example, use `printf %q` to shell-quote each variable: `nohup bash -c "sleep $DELAY_SECS && openclaw message send --target $(printf %q "$REMINDER_TARGET") --channel $(printf %q "$channel") $(printf %q "$text") && $(printf %q "$SCRIPT_PATH") remove $id" >/dev/null 2>&1 &` | LLM | scripts/nohup-reminder.sh:240 |
Scan History
Embed Code
[](https://skillshield.io/report/4676305361b27102)
Powered by SkillShield