The Agent Skills Directory

[SAFE]: The skill consists of markdown documentation and a static JSON file defining template placeholders. No code execution, privilege escalation, or persistence mechanisms were found.
[INDIRECT_PROMPT_INJECTION]: The skill defines a framework for injecting external data (e.g., CRM records, persona pain points, behavior) into generated messages via tokens like {{contact.pain_point}}. This creates a vulnerability surface where malicious instructions embedded in a CRM or database could influence the agent's output.
- Ingestion points: assets/personalization_tokens.json defines the data fields used for interpolation.
- Boundary markers: None are defined in the templates to differentiate between data and instructions.
- Capability inventory: The skill focuses on content generation for messaging, ads, and social posts; no dangerous system or network capabilities are invoked.
- Sanitization: The skill does not provide mechanisms to filter or sanitize the external data before interpolation.

personalization