po4yka/llm-wiki-skills / skills/llm-wiki-threat-model
llm-wiki-threat-model
VerifiedBuild 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.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 7.0 KB |
| references/docs/19-security-threat-model.md | markdown | 23.0 KB |
| references/policies/redaction-retention-policy.md | markdown | 3.7 KB |
| references/policies/review-incident-response.md | markdown | 3.1 KB |
| references/templates/llm-wiki-security.github-actions.yml | config | 2.9 KB |
| references/templates/mcp-security-profile.yaml | config | 3.6 KB |
| references/templates/promptfoo-llm-wiki-redteam.yaml | config | 3.8 KB |
| references/templates/security-scorecard.yaml | config | 4.0 KB |
references/templates/security-scorecard.yaml
View on GitHub# LLM-Wiki security scorecard template
# Use with llm-wiki-threat-model and llm-wiki-security-review.
metadata:
scorecard_id: "llm-wiki-security-scorecard"
version: "0.1.0"
generated_at: "YYYY-MM-DDTHH:MM:SSZ"
system: ""
deployment: local-first # local-first|localhost-http|remote-mcp|hosted-product|team-repo|hybrid
reviewer: ""
risk_profile: low # low|medium|high|critical
notes: ""
summary:
decision: continue # continue|continue-with-gates|pause|redesign|block-release
overall_status: report-only # pass|fail|warn|report-only
critical_findings: []
high_findings: []
required_actions: []
ingestion:
parser_sandbox: unknown # pass|warn|fail|unknown
file_type_allowlist: unknown
file_size_limits: unknown
parser_cve_review: unknown
no_secrets_in_parser_worker: unknown
quarantine_before_parse: unknown
extraction_hashes_recorded: unknown
findings: []
raw_and_wiki_storage:
raw_sources_classified: unknown
source_manifests_exist: unknown
provenance_hashes_exist: unknown
review_state_schema: unknown
quarantine_state_supported: unknown
immutable_raw_sources: unknown
findings: []
retrieval_and_indexes:
reviewed_only_default: unknown
tenant_filters: unknown
sensitivity_filters: unknown
publication_state_filters: unknown
stale_content_excluded: unknown
draft_rejected_quarantined_excluded: unknown
indexes_rebuildable: unknown
vector_index_classified: unknown
findings: []
prompt_injection:
untrusted_content_policy: unknown
tool_policy_server_side: unknown
public_private_stage_separation: unknown
indirect_prompt_injection_tests: unknown
malicious_source_fixtures: unknown
findings: []
mcp_api:
transport: stdio # stdio|localhost-http|remote-http|mixed|unknown
auth_required: unknown
localhost_bind: unknown
origin_validation: unknown
dns_rebinding_protection: unknown
read_propose_admin_split: unknown
admin_tools_disabled_by_default: unknown
tool_outputs_bounded: unknown
audit_sensitive_reads: unknown
no_token_passthrough: unknown
findings: []
writes_and_governance:
proposal_only_agents: unknown
codeowners: unknown
branch_protection: unknown
required_checks: unknown
self_approval_blocked: unknown
protected_human_sections: unknown
security_review_for_workflows_tools_policies: unknown
findings: []
data_protection:
secret_scan_ci: unknown
secret_scan_precommit: unknown
pii_scan_before_index_export: unknown
redaction_manifest: unknown
traces_private_by_default: unknown
retention_policy: unknown
export_allowlist: unknown
findings: []
ci_supply_chain:
dependency_review: unknown
osv_or_equivalent: unknown
sast: unknown
actions_pinned_by_sha: unknown
minimal_github_token_permissions: unknown
restricted_self_hosted_runners: unknown
findings: []
red_team:
rag_poisoning_tests: unknown
indirect_prompt_injection_tests: unknown
mcp_tool_abuse_tests: unknown
canary_secret_tests: unknown
pii_leakage_tests: unknown
export_oversharing_tests: unknown
findings: []
incident_response:
quarantine_policy: unknown
disable_external_access_procedure: unknown
secret_rotation_procedure: unknown
reindex_from_known_good: unknown
audit_log_preservation: unknown
post_incident_regression_test: unknown
findings: []
threat_matrix:
- threat: "Indirect prompt injection causing exfiltration or unsafe tool use"
likelihood: high
impact: critical
detection_difficulty: high
status: unknown
controls: []
- threat: "Corpus poisoning or durable wiki corruption"
likelihood: high
impact: high
detection_difficulty: high
status: unknown
controls: []
- threat: "Parser exploitation during ingestion"
likelihood: medium
impact: critical
detection_difficulty: medium
status: unknown
controls: []
- threat: "Secret or PII leakage through wiki, index, trace or export"
likelihood: high
impact: high
detection_difficulty: medium
status: unknown
controls: []
next_actions:
- priority: high
owner: ""
action: ""
due: "YYYY-MM-DD"
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| 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: 472k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 472k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 196k | Updated | Claude CodeCodex | Verified | Install |