Back to skill

Security audit

Phantra AI: Client Treatment

Security checks for vulnerabilities and agentic risk

Overview

This skill drafts client pitches from project materials, with disclosed download links and optional template saving.

Review the pitch for confidential project details before sending it. Anyone holding a generated download link can access the selected clip until expiry, up to seven days. Save a template only if you want its text retained. The publisher should fix the frontmatter formatting; manual inspection covered the sole artifact, but backend tools were outside the package.

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