Security audit
pizarra-explicativa-f100k
Security checks for vulnerabilities and agentic risk
Overview
The skill is a disclosed video-to-whiteboard workflow that reads user-provided media/transcripts, asks approval before paid generation, and writes expected output files.
Before installing, confirm you are comfortable giving the agent access to the local video/SRT and allowing it to use external media-generation tools that may incur cost. The skill explicitly requires user approval before paid Higgsfield generation and does not show persistence or hidden data handling.
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.