The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes brand data and LLM responses fetched from the Ubersuggest API, which creates a potential surface for indirect prompt injection from the external content being analyzed.
Ingestion points: The brand_prompts and brand_visibility_overview tools in SKILL.md retrieve external data.
Boundary markers: No explicit boundary markers are used to separate tool output from instructions.
Capability inventory: The skill uses Ubersuggest MCP tools for SEO and visibility metrics.
Sanitization: No content sanitization is specified for the ingested data.

ai-visibility