The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the Bash tool to execute a series of Python scripts and shell commands to orchestrate campaign activation across multiple platforms. These commands include curl for landing page verification and script calls for CRM, email, and ad platform updates.
[PROMPT_INJECTION]: The skill processes campaign data from a JSON file and uses it to parameterize its execution logic, presenting an indirect prompt injection vulnerability surface.
Ingestion points: The skill reads campaign plan data from the local file system at ~/.claude-marketing/brands/{slug}/campaigns/{campaign_id}/plan.json.
Boundary markers: There are no explicit instructions to ignore embedded instructions within the ingested JSON fields.
Capability inventory: The skill has broad execution capabilities, including shell access, file read/write, and network interactions via external scripts.
Sanitization: The skill lacks explicit sanitization for external data fields like {landing_url} before they are interpolated into shell commands.

launch-campaign