The Agent Skills Directory

[COMMAND_EXECUTION]: The skill invokes the command line to check for the 'monolith' utility and to perform the bundling operation. It uses variables for input and output paths which, if not properly handled by the agent platform, could be susceptible to command injection if filenames contain shell metacharacters.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-provided HTML files, creating a surface for instructions embedded in that data to influence the agent.
Ingestion points: The <input.html> file referenced in the instructions and argument hint.
Boundary markers: No explicit boundary markers or instructions to treat input file content as data only (rather than instructions) are present.
Capability inventory: The skill has access to Read, Write, and Bash tools as specified in the frontmatter.
Sanitization: There is no evidence of sanitization or content filtering for the input HTML before it is processed by the bundling tool.

export-standalone