The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill provides instructions to install the rhwp CLI utility using cargo install rhwp or by downloading pre-built binaries from a GitHub repository (https://github.com/edwardkim/rhwp/releases). These sources are outside the predefined trusted vendor list, representing a dependency on third-party code.
[COMMAND_EXECUTION]: The skill's primary workflow involves executing the rhwp binary with multiple subcommands (e.g., info, export-svg, dump, convert) to perform file operations. This execution model relies on the integrity of the external binary and the proper handling of file paths.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes HWP/HWPX documents which may contain untrusted content that could influence the agent's behavior during analysis or output generation.
Ingestion points: Reads and parses local HWP/HWPX files (e.g., sample.hwp, locked.hwp) via the rhwp CLI.
Boundary markers: None identified; document content is processed without explicit delimiters or instructions to the agent to ignore embedded commands.
Capability inventory: Executes shell commands via the rhwp CLI to generate SVG/PDF files, JSON dumps, and modified HWP files.
Sanitization: No explicit sanitization or validation of the HWP document content is performed before processing or displaying output.

rhwp-advanced