The Agent Skills Directory

[DATA_EXFILTRATION]: The tool includes a --deliver webhook:<url> parameter that allows the agent to send command outputs to an arbitrary external URL. This facilitates the exfiltration of sensitive information retrieved from TickTick, such as daily notes, task lists, and focus records.
[DATA_EXFILTRATION]: The feedback command allows sending data to a remote endpoint if TICKTICK_FEEDBACK_ENDPOINT is configured.
[PROMPT_INJECTION]: The skill ingests and processes potentially untrusted content from the user's TickTick account (tasks, notes, habits), creating an indirect prompt injection surface.
Ingestion points: Commands such as review, agenda, and tasks list retrieve content from TickTick into the agent's context.
Boundary markers: The skill does not provide instructions to wrap retrieved data in delimiters or warn the agent to ignore embedded instructions.
Capability inventory: The agent has access to Read Bash to execute the CLI, the ability to modify notes via note edit, and network exfiltration capabilities via the webhook sink.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from the external TickTick API before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the ticktick-pp-cli and ticktick-pp-mcp binaries from the vendor's GitHub repository (github.com/mvanhorn/printing-press-library) or via NPM (@mvanhorn/printing-press-library).
[COMMAND_EXECUTION]: The skill operates by executing shell commands using the ticktick-pp-cli binary.

pp-ticktick