The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions direct the agent to execute shell commands using npx @useclawlink/cli for authentication and Postmark operations.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx to fetch the @useclawlink/cli package from the NPM registry. This is a standard distribution method for the tool provided by the skill author.
[INDIRECT_PROMPT_INJECTION]: The skill features a data ingestion surface by reading external data from Postmark (e.g., email delivery statistics and bounce logs).
Ingestion points: API responses from actions like postmark_get_bounces and postmark_get_delivery_stats defined in SKILL.md.
Boundary markers: None specified in the prompt instructions to delimit external data from agent commands.
Capability inventory: The skill has the capability to execute shell commands via the ClawLink CLI.
Sanitization: No sanitization of the retrieved external content is described in the skill instructions.

postmark