The Agent Skills Directory

[SAFE]: The skill provides a structured template for executive reporting. It does not contain any obfuscated code, remote downloads, or credential-harvesting patterns.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process internal documentation and external metrics to generate reports. While this creates an attack surface for indirect prompt injection, the protocol includes explicit defensive instructions to treat external data as hostile and to redact sensitive information before processing.
Ingestion points: The skill reads from docs/departments/Executive/founder-context.md and uses search tools to gather metrics.
Boundary markers: None explicitly present in the skill body.
Capability inventory: Access to run_shell_command, write_file, and replace as defined in the skill tools.
Sanitization: The protocol explicitly instructs the agent to redact secrets/PII and treat external data as hostile.

board-update