The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes and follows instructions from untrusted local files (ad-process.md, ad-brief.md) without validation or boundary markers.
Ingestion points: Content is read from ad-process.md and ad-brief.md in the project root.
Boundary markers: No delimiters or instructions are used to distinguish user data from agent instructions.
Capability inventory: The agent can execute system commands via the AdKit CLI and read/write files in the project directory.
Sanitization: Content from the configuration files is used directly without escaping or sanitization.
[COMMAND_EXECUTION]: The skill directs the agent to execute the author's adkit CLI commands (e.g., adkit status, adkit meta campaigns create) to manage advertising accounts and campaigns.
[EXTERNAL_DOWNLOADS]: The skill recommends installing a supplementary component using npx skills add adkit-so/ads-skills --skill ad-brief to handle advertising brief generation.

meta-ads