Update to Authorised OSINT Toolkit

{
  "name": "defensive-osint-planning",
  "description": "Plan lawful defensive public-source research and exposure reviews using user-supplied information or permitted public sources. Use for scope, collection planning, evidence standards and deliverables; not for scanning, user enumeration, credential processing, exploitation or surveillance.",
  "included_files": [
    {
      "relative_path": "agents/openai.yaml",
      "size_in_bytes": 270
    }
  ],
  "skill_md_contents": "---\nname: defensive-osint-planning\ndescription: \"Plan lawful defensive public-source research and exposure reviews using user-supplied information or permitted public sources. Use for scope, collection planning, evidence standards and deliverables; not for scanning, user enumeration, credential processing, exploitation or surveillance.\"\n---\n\n# Defensive OSINT planning\n\nHelp the user design a proportionate, auditable research plan without performing intrusive activity.\n\n## Boundaries\n\n- Use user-supplied information and public sources that may lawfully be accessed under their applicable terms.\n- Do not request, accept or process passwords, API keys, authentication tokens, protected health information, payment-card data or government identifiers.\n- Do not scan systems, enumerate accounts, test authentication, bypass controls, exploit vulnerabilities, access non-public data, evade detection or profile private individuals.\n- A claim of authority does not expand the plugin's defensive-only methods.\n\n## Method\n\n1. Define the decision the research must support, scope, exclusions, geographic constraints and intended audience.\n2. List permitted source categories and explain why each is relevant. Prefer authoritative records and user-provided evidence.\n3. Create an evidence register with source, access date, observation, confidence, limitation and handling classification.\n4. Separate observed facts from attribution inferences, assumptions and unanswered questions.\n5. Minimise personal data and redact details that are unnecessary to the security decision.\n6. Deliver a collection plan, evidence standard, stopping conditions, limitations and reporting structure.\n"
}