Back to skill

Security audit

Lunar Reminder

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent lunar reminder tool, but its documented cron commands can run unsafe shell input from reminder names.

Install only if you are comfortable with this skill creating and removing OpenClaw cron reminders. Avoid untrusted reminder names, especially names containing shell syntax, until the author adds input validation, safe command invocation, explicit deletion confirmation, timezone configurability, and pinned dependencies.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
SKILL.md:113
Finding

Shell Command Injection Through Attacker-Controlled Event Names

Content
View full analysis
" ``` At lines 113-118: ```bash # 先删除旧任务 openclaw cron rm "lunar_<事件名>" # 创建新任务 openclaw cron add --name "lunar_<事件名>" --cron "<分> <时> <日> <月> *" --message "🔔 农历提醒:<事件名>将在天后到来" --tz "Asia/Shanghai" ``` ### Technical Analysis The workflow instructs the agent to extract an event name from user input and interpolate it directly into shell commands. Although the interpolated values are enclosed in double quotes, double-quoted shell strings still evaluate command substitutions using `$(...)` or backticks. The instructions do not require validation, shell escaping, or execution through an argument-array API with shell interpretation disabled. The affected values appear in both the cron task name and message. Consequently, a malicious event name can alter shell behavior when the deletion or synchronization workflow executes the generated command. ### Attack Path 1. An attacker asks the agent to create a reminder with an event name containing shell command substitution, such as `$(touch /tmp/lunar-pwned)`. 2. The workflow accepts and stores the event name in `data/events.json` without defining any security validation. 3. The attacker requests reminder synchronization or deletion. 4. The agent substitutes the stored event name into an `openclaw cron rm` or `openclaw cron add` shell command. 5. The shell evaluates the command substitution before invoking `openclaw`. 6. The injected command runs with the operating-system permissions of the agent process. ### Impact Assessment Successful exploitation provides arbitrary command execution under the account running the agent. The attacker could read or modify files accessible to that account, steal locally available credentials, disrupt application data, invoke other installed utilities, ...[truncated 217 chars]
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
package.json:6
Finding

Non-Deterministic Third-Party Dependency Installation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest presents the skill as a lunar reminder/date-conversion utility, but the instructions also direct the agent to delete reminder data and manage cron jobs. That mismatch expands the effective privilege/behavior surface beyond what a reviewer or user would expect, increasing the chance of unsafe execution or unauthorized task scheduling/deletion. In this context, the hidden operational capability is more dangerous because cron manipulation affects persistent system behavior, not just local date conversion.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The deletion flow removes both stored reminder data and a cron job without any confirmation or warning step. This creates a straightforward risk of accidental or manipulated destructive actions, especially if the agent misparses the target event name or the user did not intend to remove persistent scheduled behavior.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill documentation instructs the agent to perform system cron management, which is a materially more sensitive capability than simple reminder bookkeeping or lunar date conversion. Allowing a reminder skill to create and remove scheduled jobs can be abused to establish persistence, alter future agent behavior, or delete legitimate scheduled tasks if names collide or inputs are mishandled.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Hardcoding the cron time zone to Asia/Shanghai without user opt-in can cause reminders to fire at incorrect times for users in other locales. While not typically a code-execution issue, it can still create integrity and reliability problems for time-sensitive reminders and may surprise users by silently imposing an unintended locale assumption.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill hard-codes the timezone to Asia/Shanghai, which can cause reminders and date conversions to be wrong for users in other regions if their actual locale/timezone differs. In a lunar calendar reminder skill, timezone directly affects reminder timing and potentially date conversion boundaries, so forced configuration increases the chance of incorrect or unexpected behavior.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
92% confidence
Finding

The dependency is version-ranged with a caret (^1.6.12), so installs may resolve to newer patch/minor releases without explicit review. This creates a supply-chain risk because a compromised or breaking upstream release could be pulled into the skill unexpectedly, even though the package itself appears ordinary and the skill context does not increase the danger beyond normal dependency risk.

Content

Scanner excerpt · package.json (reported line 7)May include surrounding context.

json
"description": "按农历日期设置提醒(生日、节日等)",
  "private": true,
  "dependencies": {
    "lunar-javascript": "^1.6.12"
  }
}