task-planning-shrimp
Pass
Audited by Gen Agent Trust Hub on Feb 21, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No instructions were found that attempt to override the AI agent's safety filters or core operating guidelines.
- [Data Exposure & Exfiltration] (SAFE): There are no hardcoded credentials, sensitive file paths, or unauthorized network operations.
- [Remote Code Execution] (SAFE): The skill does not download or execute any remote scripts or untrusted packages.
- [Indirect Prompt Injection] (SAFE): The skill processes user input to structure task lists via MCP tools. While it lacks explicit boundary markers for untrusted data, the logic is strictly functional for its stated purpose as a task manager.
Audit Metadata