The Agent Skills Directory

[PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it reads and processes data from external sources (event_candidates YAML) and the local filesystem to generate its output.
Ingestion points: The skill ingests event_candidates YAML and reads local source code files identified by the file field in that YAML. It also reads a taxonomy skill file.
Boundary markers: There are no specified delimiters or instructions to ignore embedded commands within the processed files or YAML data.
Capability inventory: The skill is capable of reading files from the local filesystem.
Sanitization: The skill does not implement validation for the input file paths or sanitization of the content read from those files.

instrument-events