Back to skill

Security audit

Olares Market (olares-cli market)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed command guide for managing Olares Market apps, including expected app and chart changes.

Install this only if you want an agent to help manage Olares Market apps through olares-cli. Review destructive requests carefully: uninstall, stop, cancel, cascade actions, and chart delete can interrupt apps or remove local chart packages, so confirm app names and versions before allowing those commands.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly enables destructive and state-changing operations such as install, upgrade, uninstall, stop, resume, cancel, upload, and delete, but the top-level description does not warn that these actions can modify or remove user applications and charts. In an agent setting, that omission increases the risk that the model will select and invoke the skill for unsafe requests without first surfacing consequences or confirming user intent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This documentation describes destructive operations such as uninstall, stop, and cancel, including options like cascade removal, but does not include an explicit warning about service disruption, data loss, or irreversible effects. In an agent skill context, these commands may be executed on a user's behalf, so omission of clear safety guidance increases the chance of accidental harmful actions even if the commands themselves are legitimate product functionality.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The natural-language examples include a specific non-English phrase alongside English phrases as if they are the expected supported triggers, but the file does not state whether language handling is optional, user-selected, or region-specific. Under the policy, forcing or assuming a specific language/locale without opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.