The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script to perform health monitoring and reporting tasks.
Evidence: Invokes campaign-health-monitor.py with subcommands health-score, corrections-history, and savings-report.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting data from external configuration files and agency SOPs.
Ingestion points: Reads brand profile data from ~/.claude-marketing/brands/{slug}/profile.json and agency procedures from ~/.claude-marketing/sops/.
Boundary markers: No clear delimiters or instructions to ignore embedded commands are present in the skill description.
Capability inventory: The skill has the ability to execute shell commands via the campaign-health-monitor.py script.
Sanitization: No sanitization or validation of the content within the JSON profiles or SOP files is documented.

autopilot-status