メニュー
Query the mesh's threat library for entries matching a concern (e.g. "identity", "data-licensing").
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | knowledge-mesh-threats |
| description | Query the mesh's threat library for entries matching a concern (e.g. "identity", "data-licensing"). |
| version | 0.1.0 |
| purity | pure-data |
| runtime | research-runner |
| command | npx @maintainabilityai/research-runner@~0.1.64 skill-knowledge-mesh-threats |
Returns STRIDE entries from threats/ that match the concern. Used by prd-agent (during its Security persona-switch) + code-design-agent (during its Code-Security persona-switch) to ground security sections. (Pre-B24 was also consumed by a separate security-reviewer agent; that dispatch was retired — persona-switch self-critique inside the author agent replaced it.)
| Field | Type | Required | Default | Description |
|---|---|---|---|---|
concern | string | yes | — | A tag or free-text concern (e.g. identity-disambiguation, data-licensing). |
maxResults | integer | no | 20 |
| Field | Type | Description |
|---|---|---|
ok | boolean | |
threats | ThreatEntry[] | Entries with id, category, description, nistControls[], owaspCategories[]. |
echo '{"concern":"identity-disambiguation"}' \
| npx @maintainabilityai/research-runner@~0.1.64 skill-knowledge-mesh-threats
Walks threats/ library, filters by tag/keyword match. Implemented by the knowledge-mesh-threats handler in packages/research-runner/src/runner/skills.ts (walks the top-level threats/ library + each <bar>/architecture/threat-model.yaml).
Empty threats: [] is NOT an error — returns ok: true with no matches.
Append one hash-chained audit event to okrs/<id>/audit/events/<run-id>.jsonl. Returns the new chain head.
Replay the hash chain over an existing audit JSONL; returns the chain head on success, the first integrity failure reason on failure.
Academic paper search via arXiv. Returns ranked paper results per query envelope.
Aggregated architecture context for a scope — CALM nodes + ADRs + fitness functions + quality attributes. PURE data; the Architect persona is in the parent agent's prompt.
Aggregated quality context for a scope — quality attribute definitions + performance SLOs + reliability targets per BAR.
Aggregated security context for a scope — STRIDE threats + OWASP refs + NIST controls + prior threat-model docs. PURE data; the Security persona is in the parent agent's prompt.