apple-voice-memos

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes two internal Python scripts (extract-apple-voice-memos-metadata and extract-apple-voice-memos-transcript) using the system's python3 interpreter to interact with local system files.
  • [DATA_EXFILTRATION]: Accesses the local iCloud Voice Memos database at ~/Library/Group Containers/group.com.apple.VoiceMemos.shared/Recordings/CloudRecordings.db and associated recording files. While this is the skill's primary purpose, these files contain sensitive user metadata and audio recordings. The metadata script uses SQLite's read-only mode for safety.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface by processing user-generated voice memo transcripts and interpolating them into subagent instructions.
  • Ingestion points: Transcripts are extracted from .m4a files via scripts/extract-apple-voice-memos-transcript and passed to a subagent.
  • Boundary markers: The PROMPT.md file uses a ## Transcript header to delimit the untrusted content.
  • Capability inventory: The skill uses python3 for database queries and file reads; it does not request network access in its allowed-tools configuration.
  • Sanitization: The script performs regex-based cleaning of speech disfluencies (filler words and repetitions) but does not validate the content against malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 11:33 AM