The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process content from external competitor websites, social media platforms, and advertising libraries to generate intelligence reports.
Ingestion points: External competitor URLs, product JSON data, and ad library content (referenced in SKILL.md and references/multi-dimensional-analysis.md).
Boundary markers: The skill incorporates a specific 'Anti-patterns & Boundaries' file (references/anti-patterns.md) and a 'Visibility Loading' protocol to guide agent behavior, although it lacks explicit delimiters for external data interpolation within the prompt templates.
Capability inventory: The agent is instructed to write analytical findings, strategy reports, and 'learnings' to the brand-brain/ directory (as described in the 'Completion Protocol' and SKILL.md).
Sanitization: No specific mechanisms for sanitizing or escaping external content before it enters the agent's context were found in the instructions.

afa-compete