Security audit
visual-refresh
Security checks for vulnerabilities and agentic risk
Overview
This skill provides clearly disclosed instructions for editing existing Canvora visuals, including credit costs and undo options.
Expect requested edits and variations to consume Canvora credits; localization and variations affect the whole selected generation. Set a spending limit and verify the target IDs. Undo restores visuals but does not necessarily refund credits. The separate CLI and setup skill were outside this package 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