The Agent Skills Directory

[DATA_EXPOSURE]: The skill accesses a local file at ~/.claude/company-context.md containing sensitive business data such as revenue, burn rates, and runway. This is the intended purpose of the skill for maintaining session context.
[DATA_EXFILTRATION]: The skill explicitly defines 'Privacy Rules' and an 'Anonymization Protocol' in references/anonymization-protocol.md. Internal instructions mandate that the agent must strip or generalize sensitive figures (e.g., converting specific ARR to ranges) before any data leaves the local environment via external tool or API calls.
[COMMAND_EXECUTION]: The skill does not contain executable scripts or shell commands. It uses natural language instructions to guide the agent's interaction with the file system and external tools.

context-engine