notes-automation-workflows
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends that the user install a third-party Homebrew package "antoniorodr/memo/memo". This introduces an external dependency from an unverified source into the execution environment.
- [COMMAND_EXECUTION]: The skill uses "osascript" to execute AppleScript strings on the host macOS system. This provides the agent with the ability to programmatically search, read, and modify any content within the user's Apple Notes application.
- [PROMPT_INJECTION]: The skill operates on untrusted data from the user's notes, creating a surface for indirect prompt injection.
- Ingestion points: Note bodies and metadata are retrieved via "osascript" calls in "SKILL.md".
- Boundary markers: There are no markers or delimiters used to separate note content from the agent's instructions during processing.
- Capability inventory: The skill possesses the ability to read and write notes via "osascript" and the "memo" CLI tool.
- Sanitization: There is no evidence of content sanitization or escaping before the data is processed for enrichment or summarization.
Audit Metadata