Skip to content

po4yka/llm-wiki-skills / skills/llm-wiki-threat-model

llm-wiki-threat-model

Verified

Build a formal security architecture threat model for an LLM-Wiki system. Use when the user asks for STRIDE, LINDDUN, PASTA, data-flow diagrams, trust boundaries, attack-surface mapping, abuse cases, risk matrices, red-team scenarios, or control baselines; route existing-config safety reviews to llm-wiki-security-review.

references/templates/mcp-security-profile.yaml

View on GitHub
# LLM-Wiki MCP/API security profile template
# Use with llm-wiki-threat-model, llm-wiki-security-review and llm-wiki-mcp-integration.

name: llm-wiki-mcp
version: "0.1.0"
owner: ""
reviewed_at: "YYYY-MM-DD"

transport:
  preferred: stdio # stdio|localhost-http|streamable-http|mixed
  allow_stdio: true
  allow_http: false
  allow_remote_http: false

http:
  bind: 127.0.0.1
  path: /mcp
  auth_required: true
  origin_validation: true
  dns_rebinding_protection: true
  rate_limits:
    search_per_minute: 60
    read_per_minute: 300
    proposal_per_minute: 10
    admin_active_tasks_per_user: 1

auth:
  mode: local-token # local-token|api-key|oauth2|enterprise-managed|github-app|none
  allow_none: false
  scopes:
    wiki:read:
      description: Search/read allowed wiki resources.
    wiki:lint:
      description: Run/read bounded lint reports.
    wiki:propose:
      description: Create proposals/patches only.
    wiki:review:
      description: Review proposals.
    wiki:admin:
      description: Reindex, rescan, export, publish or approve.
  token_passthrough_allowed: false

resources:
  read_only:
    - wiki://manifest
    - wiki://index
    - wiki://page/{space}/{slug}
    - wiki://page/{space}/{slug}/history
    - wiki://page/{space}/{slug}/lint
    - wiki://manifest/{source_id}
    - wiki://graph/neighbors/{space}/{slug}
    - wiki://review/unresolved
  forbidden_by_default:
    - raw://source/{source_id}/content
    - file://*

tools:
  read_only:
    - name: search_wiki
      required_scope: wiki:read
      enabled_for_cloud_clients: true
    - name: read_page
      required_scope: wiki:read
      enabled_for_cloud_clients: true
    - name: read_source_manifest
      required_scope: wiki:read
      enabled_for_cloud_clients: false
    - name: graph_neighborhood
      required_scope: wiki:read
      enabled_for_cloud_clients: true
    - name: run_lint
      required_scope: wiki:lint
      enabled_for_cloud_clients: false
  proposal_write:
    - name: draft_page_patch
      required_scope: wiki:propose
      enabled: false
      creates_direct_write: false
    - name: propose_new_page
      required_scope: wiki:propose
      enabled: false
      creates_direct_write: false
    - name: create_pr_from_proposal
      required_scope: wiki:propose
      enabled: false
      creates_direct_write: false
  admin:
    - name: rebuild_index
      required_scope: wiki:admin
      enabled: false
    - name: rescan_sources
      required_scope: wiki:admin
      enabled: false
    - name: export_subset
      required_scope: wiki:admin
      enabled: false
    - name: approve_proposal
      required_scope: wiki:admin
      enabled: false

retrieval_policy:
  production_review_states:
    - approved
    - verified
    - published
  excluded_review_states:
    - draft
    - rejected
    - stale
    - quarantined
  required_filters:
    - tenant_id
    - sensitivity
    - review_state
    - publication_state
  allow_raw_source_reads_in_high_privilege_flows: false
  allow_unreviewed_retrieval: false

approvals:
  require_user_confirmation_for:
    - proposal_write
    - admin
  require_codeowners_for:
    - wiki/policies/**
    - wiki/security/**
    - .github/**
    - templates/**
    - skills/**
    - policies/**
  self_approval_allowed: false

audit:
  enabled: true
  destination: .llm-wiki/audit.jsonl
  include_sensitive_arguments: false
  include_argument_hash: true
  events:
    - sensitive_read
    - proposal_created
    - proposal_approved
    - admin_tool_invoked
    - export_created
    - denied_tool_call

security_tests:
  prompt_injection_fixtures: true
  mcp_tool_abuse_tests: true
  canary_secret_tests: true
  cross_tenant_tests: true
  export_redaction_tests: true
rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first.Stars: 194kUpdated Claude CodeCodexVerifiedInstall