The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the kai-gate CLI tool in Step 6 to evaluate the quality of the generated ad copy. This is a local execution path for internal scoring purposes.
[PROMPT_INJECTION]: The skill processes content from local markdown files including policies and marketing briefs, which represents an attack surface for indirect prompt injection where instructions embedded in those files could influence agent behavior. 1. Ingestion points: Local files in harness/references/ and ~/.kai-marketing/briefs/ as defined in SKILL.md. 2. Boundary markers: None specified to differentiate between provided data and instruction context. 3. Capability inventory: Shell execution capability via the kai-gate command as defined in SKILL.md. 4. Sanitization: No specific filtering or escaping mechanisms for the imported text are described.

ad-copy