The Agent Skills Directory

[DATA_EXFILTRATION]: Accesses a sensitive local file path at ~/.config/notion/api_key to retrieve the user's Notion API key. While this is necessary for the skill's primary functionality, accessing credential files in the home directory is a sensitive operation.
[COMMAND_EXECUTION]: Executes shell commands including remindctl, curl, and jq in the scripts/generate-briefing.sh file to aggregate and process data.
[DATA_EXFILTRATION]: Communicates with the external Notion API (api.notion.com) to retrieve task data. This is a well-known service, and the operation is consistent with the skill's stated purpose.
[PROMPT_INJECTION]: The skill ingests untrusted data from Apple Reminders and Notion, which provides a surface for indirect prompt injection.
Ingestion points: The script scripts/generate-briefing.sh reads data from the output of remindctl and the JSON response from the Notion API.
Boundary markers: Absent; the ingested data is not delimited or wrapped in instructions to prevent the agent from following embedded commands.
Capability inventory: The skill has access to shell execution and network operations through scripts/generate-briefing.sh.
Sanitization: Absent; the script performs basic formatting using awk and jq but does not sanitize or escape content to prevent malicious instructions from influencing the agent's logic.

morning-briefing