The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for the agent to use network diagnostic tools, specifically curl -I to verify HTTP 301 redirect statuses and dig to confirm DNS propagation. These are standard operations for validating a website migration.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, potentially untrusted sources which creates an attack surface for indirect prompt injection.
Ingestion points: The skill collects data from CMS exports, XML sitemaps, server logs, and analytics tools as described in Phase 1: Inventory of SKILL.md.
Boundary markers: There are no explicit instructions or delimiters provided to prevent the agent from obeying instructions that might be embedded within the processed inventory data.
Capability inventory: The skill uses curl and dig for network verification, which have limited exploitation potential but are present in the references/migration-runbook.md file.
Sanitization: The skill lacks explicit sanitization or filtering steps for the content found in the external data sources.

content-migration