quick-note

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns such as data exfiltration, obfuscation, or unauthorized remote code execution were found. All operations are restricted to the local filesystem and are consistent with the skill's primary purpose.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it stores and later retrieves arbitrary user-provided text.
  • Ingestion points: Note content parsed in the 'Save Note' workflow and stored in markdown files within ~/notes/.
  • Boundary markers: Entries are partitioned using markdown headers and horizontal separators (---), though it lacks explicit instructions to ignore commands within the notes.
  • Capability inventory: The skill utilizes file system read/write access and shell command execution of 'Grep' for search operations.
  • Sanitization: No sanitization or validation of note content or search patterns is specified in the workflow instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 07:05 PM