Back to skill

Security audit

Phantra AI: Browse Presets

Security checks for vulnerabilities and agentic risk

Overview

This skill presents creative-tool options and requires a quoted price and explicit approval before any paid action.

The reviewed instructions are limited to browsing and user-directed selection. SkillSpector reported partial coverage but no findings; full manual inspection found no material security concern. Correct the frontmatter formatting for reliable loading, and review the separate tools and skills before authorizing uploads or paid execution.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep