query-taiwan-holiday

Fail

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides instructions to download a shell script from the author's repository and pipe it to a shell for execution (https://raw.githubusercontent.com/doggy8088/holidaybook/master/install.sh).
  • [COMMAND_EXECUTION]: The skill uses PowerShell to download and execute remote content via Invoke-Expression (https://raw.githubusercontent.com/doggy8088/holidaybook/master/install.ps1).
  • [DYNAMIC_EXECUTION]: The skill utilizes runtime shell execution and script piping as primary installation mechanisms.
  • [EXTERNAL_DOWNLOADS]: The skill attempts to install and run the holidaytw package from the npm registry using npx.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from an external API (https://holiday.gh.miniasp.com), which represents a vulnerability surface.
  • Ingestion points: Remote JSON holiday data is retrieved in SKILL.md.
  • Boundary markers: The prompt includes instructions for strict date validation and JSON parsing.
  • Capability inventory: The agent has access to curl, npx, and shell execution tools.
  • Sanitization: The instructions mandate strict validation of date formats and rejection of malformed JSON structures.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/doggy8088/holidaybook/master/install.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Oct 24, 2026, 06:24 AM