korean-holiday-calendar

Warn

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions in SKILL.md direct the agent to run npx -y @nomadamas/k-skill@0, which downloads code from the NPM registry to provide dynamic instructions and updates.
  • [REMOTE_CODE_EXECUTION]: The use of npx to fetch and execute the @nomadamas/k-skill package constitutes the execution of unverified external code within the agent's environment.
  • [COMMAND_EXECUTION]: The skill uses curl to make network requests to an external proxy server (k-skill-proxy.nomadamas.org) to retrieve holiday data.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from a third-party API, creating a surface for potential instruction injection if the upstream content is modified by an attacker.
  • Ingestion points: instruction.md fetches data via curl from https://k-skill-proxy.nomadamas.org/v1/korean-holiday/calendar.
  • Boundary markers: None present; the skill lacks delimiters or warnings to ignore instructions that might be embedded in the API response.
  • Capability inventory: The skill utilizes curl for network access and npx for command execution/package management.
  • Sanitization: No evidence of sanitization or validation of the external API response before the agent processes it.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 1, 2026, 02:41 PM