The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx -y @nomadamas/k-skill@0 to download and execute instructions, files, and updates from the NPM registry at runtime.
[REMOTE_CODE_EXECUTION]: The instruction set explicitly directs the agent to run npx -y @nomadamas/k-skill@0 instruct kakao-map to obtain the primary logic and instructions for the skill. This means the skill's behavior is dynamically determined by remote code executed on the user's machine.
[COMMAND_EXECUTION]: The skill relies on shell commands (npx, curl) to perform its primary functions, including fetching instructions and interacting with API endpoints.
[INDIRECT_PROMPT_INJECTION]: The skill processes data fetched from an external proxy (k-skill-proxy.nomadamas.org) which in turn fetches data from Kakao's APIs. Malicious or unexpected content in the API responses could potentially influence the agent's behavior.
Ingestion points: Data enters via curl requests to the k-skill-proxy endpoints in instruction.md.
Boundary markers: None identified in the provided instructions to delimit external data from agent commands.
Capability inventory: The agent has the capability to execute shell commands (curl, npx) and process JSON responses.
Sanitization: There is no explicit evidence of sanitization or validation of the external content before it is processed by the agent.

kakao-map