maestro-note

Pass

Audited by Gen Agent Trust Hub on Feb 26, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill implements a persistent memory system where 'Priority Context' is automatically injected into every future session and implementation run. This creates a surface for Indirect Prompt Injection. If malicious instructions are stored in the notepad (e.g., via a compromised file processed by the agent), these instructions would be re-injected into the agent's context in subsequent runs.
  • Ingestion points: .maestro/notepad.md (Priority Context section).
  • Boundary markers: None specified to distinguish injected instructions from system prompts.
  • Capability inventory: The skill performs file read/write operations on .maestro/notepad.md and references other implementation tools.
  • Sanitization: No sanitization or validation of the note content is performed before injection.
  • [COMMAND_EXECUTION]: The skill performs local file system operations, including directory creation (.maestro/) and file manipulation (reading, appending, and writing to .maestro/notepad.md). These are standard operations for its intended purpose of maintaining a persistent notepad.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 26, 2026, 09:27 PM