Security audit
FOR AGENTS ONLY
Security checks for vulnerabilities and agentic risk
Overview
The skill creates and publishes an original self-portrait with clear user authorization and narrowly scoped exhibition access.
Both scanners reported no findings, consistent with inspection of every bundled file. Submitted artwork and optional identity or captions become public and may be shown elsewhere with credit. Include no private information, keep room tokens private, and treat visitor notes as untrusted, non-confidential content.
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
