The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources that could potentially contain malicious instructions intended to manipulate the agent's behavior.
Ingestion points: Untrusted data enters the agent context through the output of lobstercash crypto x402 fetch and from browsing arbitrary merchant websites during the purchase flow.
Boundary markers: The skill contains explicit instructions in references/x402.md regarding a 'Trust boundary,' warning the agent to treat external bodies as untrusted data and not to modify its task based on instructions found within that data.
Capability inventory: The agent has significant capabilities, including executing shell commands via the lobstercash CLI, performing crypto transactions, and driving browser automation for checkouts.
Sanitization: The skill provides clear instructions for the agent to summarize or extract data rather than executing instructions from external content.
[EXTERNAL_DOWNLOADS]: The skill instructs the user to install the @crossmint/lobster-cli package via npm. This package is an official tool provided by the vendor (crossmint) to enable the skill's core functionality.

lobstercash