The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill instructs the agent to download and execute an external CLI tool to obtain functional instructions and files.
SKILL.md requires running npx -y @nomadamas/k-skill@0 instruct consumer-price-safety-search to get the primary instructions.
The skill also suggests running npx -y @nomadamas/k-skill@0 update to maintain the installation, which involves executing remote code from an external registry.
[EXTERNAL_DOWNLOADS]: The skill fetches core components and instructions from external, third-party sources.
Dependencies are fetched from the @nomadamas/k-skill package on the npm registry.
Documentation and instruction sources are referenced at https://github.com/NomaDamas/k-skill/blob/main/consumer-price-safety-search/instruction.md.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external consumer safety and price APIs, which could contain malicious instructions designed to influence the agent.
Ingestion points: External API responses from data.go.kr and consumer.go.kr (referenced in instruction.md).
Boundary markers: None identified in the draft scaffold to separate external data from agent instructions.
Capability inventory: The skill has the capability to execute shell commands via the suggested npx workflow.
Sanitization: No evidence of input validation or sanitization for data retrieved from external price and recall databases.

consumer-price-safety-search