Security audit
Phantra AI: Product Shots
Security checks for vulnerabilities and agentic risk
Overview
The skill guides product-image and video creation with clear user approval before spending credits.
Use a trusted Phantra connection, share only product photos you intend to upload, and review quoted credits before approving generation. Both scanners reported no findings, but SkillSpector coverage was partial; manual review found no material security concern. The frontmatter should be corrected for reliable loading, and external service behavior remains outside this review.
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
