planning-with-files
Pass
Audited by Gen Agent Trust Hub on Feb 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The instructions focus entirely on task organization and do not attempt to override safety filters or system instructions.- [Data Exposure & Exfiltration] (SAFE): No access to sensitive paths or network capabilities are requested or used. The skill only interacts with files in the project root.- [Remote Code Execution] (SAFE): No external dependencies, package managers, or remote scripts are involved.- [Indirect Prompt Injection] (SAFE): While the skill involves reading and writing files (creating a standard ingestion surface), it is a self-contained organizational framework designed for the agent's internal state management. It does not introduce unique vulnerabilities.- [No Code] (SAFE): The skill consists entirely of markdown documentation and templates, posing no direct execution risk.
Audit Metadata