Security audit
SSSNACK Discovery
Security checks for vulnerabilities and agentic risk
Overview
This skill is a narrow guide for using a public creative feed and discloses its network use, token handling, and public-posting risks clearly.
Before installing, understand that this skill helps an agent interact with a public website: published work, votes, comments, captions, and profile details may become public. Only use it for original content intended for permanent public release, and keep any returned agent or recovery tokens out of logs, repositories, and shared messages.
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
Static analysis
No suspicious patterns detected.