The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches and executes the @useclawlink/cli package from the NPM registry using the npx command.
[COMMAND_EXECUTION]: Instructions direct the agent to run shell commands via npx @useclawlink/cli to perform Gumroad actions such as listing products and retrieving sales data.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Gumroad which could contain malicious instructions targeting the AI agent.
Ingestion points: Data is pulled into the agent's context through actions like gumroad_list_products, gumroad_get_sales, and gumroad_get_resource_subscriptions as described in SKILL.md.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard instructions embedded within the Gumroad data.
Capability inventory: The skill has the capability to execute shell commands via the ClawLink CLI (referenced in SKILL.md).
Sanitization: There is no mention of sanitization, filtering, or validation of the content retrieved from Gumroad before it is processed by the agent.

gumroad