note-organizer

Pass

Audited by Gen Agent Trust Hub on May 19, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill operates entirely within the local environment, storing all note data in the user's home directory (~/.notes). No external network requests or data transmission patterns were found.\n- [COMMAND_EXECUTION]: The shell script (scripts/joplin.sh) constructs file paths using user-supplied arguments in several commands, such as 'notebook'. Although the script enforces file extensions (e.g., .md), this represents a potential directory traversal surface if an attacker provides path-relative arguments to access unintended locations.\n- [PROMPT_INJECTION]: Indirect Prompt Injection Surface.\n
  • Ingestion points: Note content is ingested into the agent context via 'view', 'search', and 'export' commands in scripts/joplin.sh.\n
  • Boundary markers: None. Note content is processed and displayed without delimiters to separate it from system instructions.\n
  • Capability inventory: The skill has file-system write capabilities through 'new', 'edit', and 'trash' commands.\n
  • Sanitization: None. The content of notes is returned to the agent without validation or escaping, which could allow malicious instructions embedded in notes to influence the agent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
May 19, 2026, 10:48 AM
Security Audit — agent-trust-hub — note-organizer