apple-notes
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the
memoCLI tool via a third-party Homebrew tap (antoniorodr/memo). This involves downloading and installing code from an external repository that is not managed by a verified organization. - [COMMAND_EXECUTION]: The skill relies on executing shell commands through the
memoutility to interact with the macOS system and manage the Apple Notes database (e.g.,memo notes -a,memo notes -e). - [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection:
- Ingestion points: The skill retrieves text content from the user's local Apple Notes database using commands like
memo notes -sormemo notes -ex(SKILL.md). - Boundary markers: No specific delimiters or instructions are provided to ensure the agent treats the retrieved note content as untrusted data.
- Capability inventory: The skill allows the agent to execute shell commands via the
memoCLI and perform write operations to the local notes storage. - Sanitization: The skill lacks mechanisms to sanitize or validate the content retrieved from notes before it is processed by the agent.
Audit Metadata