Security audit

Midlong Term Task Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a local task-tracking skill that writes task logs and reports in the OpenClaw workspace, with no evidence of hidden network, credential, or destructive behavior.

Install only if you want local task records and generated reports under ~/.openclaw/workspace/.tasks. Enable the heartbeat or cron examples only intentionally, and avoid putting secrets or highly sensitive project details in task names or descriptions because they will be retained in local logs and summaries.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (3)

Vague Triggers

Medium

Confidence: 85% confidence
Finding: The trigger conditions are broad and operationally ambiguous, especially automatic activation on heartbeat checks, status changes, and daily summaries without clear scoping, consent, or deduplication rules. In an agent environment, this can cause unintended execution and repeated writes to task/log files, increasing the chance of unauthorized persistence or disruptive behavior.

Missing User Warnings

Medium

Confidence: 92% confidence
Finding: The skill clearly states that it stores task data and logs in workspace files, but it does not provide an explicit user-facing warning or consent model for persistent writes. In agent workflows, silent persistence can expose sensitive planning data, create audit/privacy issues, and surprise users who did not intend long-term storage.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The script persistently logs task IDs, names, due dates, and progress into a predictable file under the user's home directory without any notice, consent, retention control, or permission hardening. While not an exploit by itself, this creates a privacy and confidentiality risk because potentially sensitive project/task metadata is stored long-term and may be accessible to other local processes, backups, or users depending on filesystem permissions.

Static analysis

No suspicious patterns detected.