The Agent Skills Directory

[SAFE]: The skill primarily performs local data processing and analysis. It uses the yargs library for command-line argument parsing and fs for reading local JSON files required for its function.
[PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it processes external data from JSON files.
Ingestion points: src/index.ts reads data from the file path provided in the --input argument.
Boundary markers: No boundary markers or delimiters are used when interpolating ingested data into the internal processing logic.
Capability inventory: The skill has the capability to write output files to the local file system using the safeWriteFile utility from @agent/core.
Sanitization: While the skill parses input as JSON, it does not sanitize or validate the text content within the JSON fields to prevent potential instructions embedded in the data from influencing the agent's behavior.

sunset-architect