The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes files within the current workspace, including the README, package manifests, and repository metadata, to automatically determine a project name for domain searching.
Ingestion points: Project repository metadata, package names, and README content are read into the agent's context (referenced in SKILL.md).
Boundary markers: No specific delimiters or "ignore instructions" markers are defined for the ingested workspace content.
Capability inventory: The skill utilizes tool calls for search_domains, check_domain_availability, and generate_domain_variations via the Instant Domain Search MCP.
Sanitization: The skill performs basic normalization (removing spaces and punctuation) but does not include explicit security sanitization for instructions embedded within README files or other project metadata. This presents a surface for indirect injection if project files contain adversarial content designed to influence the agent's search parameters or output.
[EXTERNAL_DOWNLOADS]: The skill refers to and utilizes the Instant Domain Search MCP service (instantdomainsearch.com), which is a well-known domain discovery service. This interaction is consistent with the skill's stated purpose of providing live domain availability data.

find-domain