The Agent Skills Directory

[PROMPT_INJECTION]: The skill documents an interface for searching historical data, creating an attack surface for indirect prompt injection.
Ingestion points: The agent is instructed to query conversations, errors, and files which may contain untrusted data.
Boundary markers: No delimiters or instructions to ignore embedded commands are specified.
Capability inventory: The skill relies on search and inspect tools.
Sanitization: No sanitization methods are mentioned in the skill documentation.

claude-historian