docs(readme): surface OKF residual risks §7.2 dormant-link + §7.4 own-security-content (T8)

README.md

@@ -107,6 +107,17 @@ that a green scan means safe content:
 - **Adversarial-ML evasion** can survive normalization; **tokenizer mismatch**
   between scanner and model leaves gaps.
 - **Latent / dormant memory poisoning** is not judgeable at write time.
+- **Dormant / broken-link injection** in a linked corpus (e.g. an OKF bundle): a
+  link to a not-yet-existing target passes a per-concept write-time scan clean —
+  the payload is planted later, when that target is written. A scanner that sees
+  one document at a time cannot catch it; it needs cross-write graph re-scan
+  (tracked for the OKF adapter).
+- **A document that *describes* attacks is a false positive.** Content whose
+  legitimate purpose is to document prompt-injection payloads (security notes,
+  this project's own corpus) trips carrier-strip / fail-secure. At the text layer
+  there is no way to distinguish "*about* an attack" from "*carrying* an attack";
+  such content needs a deliberate, explicitly-marked escaped path, never a silent
+  allow.
 - **Insider in-place edits** by a trusted author are out of the untrusted-content
   threat model.
 - **Text-only.** The core is `text -> findings`: it parses no files (no