The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to run the cass command-line utility for searching and viewing conversation history files.
[INDIRECT_PROMPT_INJECTION]: The skill processes external data (conversation history) which could theoretically contain malicious prompts from past sessions.
Ingestion points: Reads data from local session history files (e.g., .jsonl files) via cass view and cass search.
Boundary markers: Not explicitly defined in the prompt instructions.
Capability inventory: The skill primarily performs file reads and data display; no network or arbitrary code execution capabilities are defined.
Sanitization: No specific sanitization or filtering of the ingested history data is described.

cass