The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: Fetches the required CLI tool using npx from the @mvanhorn scope and go install from the vendor's GitHub repository (github.com/mvanhorn/printing-press-library). These sources are associated with the skill's author context.
[DATA_EXFILTRATION]: The skill accesses highly sensitive local databases: ~/Library/Messages/chat.db (iMessage history) and the Apple Photos library database (Photos.sqlite). While the skill's purpose is to query these, they contain private user communications and media metadata that could be exposed if handled improperly by an agent.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The messages search and messages export commands ingest untrusted content (message bodies and attachments) from the local chat.db directly into the agent's context.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the retrieved message data as untrusted or to ignore embedded instructions.
Capability inventory: The skill possesses capabilities for shell command execution (icloud-pp-cli), file writing (--out), and media deletion (via AppleScript integration).
Sanitization: The skill instructions do not specify any sanitization, filtering, or validation of the retrieved message content before it is processed by the agent.
[COMMAND_EXECUTION]: Executes the icloud-pp-cli binary to perform intensive system queries, including searching message history and managing local media storage.

icloud-pp-cli