The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs the agent to execute code from the internet using npx @aizzie/cli@latest. This command fetches and runs the most recent version of the Aizzie CLI from the npm registry each time it is invoked, which allows for the execution of remote code that has not been statically reviewed.
[EXTERNAL_DOWNLOADS]: The skill relies on the @aizzie/cli package, which is an external dependency downloaded from the public npm registry. This source is not categorized as a pre-verified or trusted vendor in the current environment.
[COMMAND_EXECUTION]: The core functionality of the skill is dependent on executing shell commands, specifically subcommands of the Aizzie CLI such as docs and place search to interact with external travel services.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (such as search results from place search and user-provided trip parameters) that could potentially contain embedded instructions meant to manipulate the agent's behavior. The instructions lack protective measures to mitigate this risk.
Ingestion points: External data enters the context via place search results and user travel descriptions as described in SKILL.md.
Boundary markers: The skill does not define delimiters or provide instructions to the agent to ignore or treat embedded commands within the travel data as plain text.
Capability inventory: The skill utilizes command execution (npx) and network operations (facilitated by the CLI) to perform its tasks.
Sanitization: There is no evidence of data validation or sanitization routines for the external place data before it is presented to the agent.

travel-companion