ClawHub
Back to skill

Security audit

Olares Market (olares-cli market)

Security checks across malware telemetry and agentic risk

Overview

This looks like a legitimate Olares app-management skill, but it needs review because it enables destructive app lifecycle actions without explicit confirmation safeguards.

Install only if you intend to let the agent manage Olares apps through your authenticated olares-cli profile. Before running uninstall, stop, cancel, upgrade, chart delete, cascade, or bulk-stop commands, require the agent to show the exact target apps and confirm the action, especially because these commands can interrupt services or remove local chart versions.

SkillSpector

By NVIDIA
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
89% confidence
Finding
The skill description and trigger text are very broad, covering many common app-management phrases and status questions. This can cause the agent to invoke this skill for ambiguous requests and perform or suggest state-changing Olares app operations in contexts where the user may not have intended Olares-specific actions, increasing the chance of mistaken installs, upgrades, stops, or removals.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
This section documents destructive lifecycle actions such as uninstall and cascade removal, but it does not clearly warn that these operations may remove app data, shared sub-charts, or affect other services in a multi-chart deployment. In an agent skill context, users may issue high-level requests and the agent could translate them directly into destructive commands, so the lack of explicit safety guidance increases the chance of accidental service or data loss.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The skill recommends piping the user's app list into a shell loop to stop everything, but it does so without warning about broad service disruption or the risk of halting critical apps for that Olares ID. In an automation-oriented agent setting, this kind of bulk action guidance can be executed quickly and at scale, turning a convenience example into an outage-causing pattern.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.