The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data by parsing source files or stdin input.
Ingestion points: File paths passed to ts-pack parse and data piped from stdin as seen in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the command examples.
Capability inventory: The skill utilizes shell execution for ts-pack, jq, cat, and printf to process and analyze code structure.
Sanitization: There is no evidence of input validation or sanitization of the source code content before it is processed by the parser.
[EXTERNAL_DOWNLOADS]: The skill documentation notes that ts-pack downloads required language grammar libraries on first use. This is documented as the standard operational behavior of the tool.

parsing-source