diff options
Diffstat (limited to 'newos4_whitepaper.md')
| -rw-r--r-- | newos4_whitepaper.md | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/newos4_whitepaper.md b/newos4_whitepaper.md index 8695eef..755ba03 100644 --- a/newos4_whitepaper.md +++ b/newos4_whitepaper.md @@ -197,6 +197,15 @@ What the whitepaper originally listed as 4 items has grown into 25+ completed fe **Implementation Plan:** `.hermes/plans/2026-06-02_phase3-cognitive-os.md` +### Phase 4 — Agent Safety Security Layer ✅ RELEASED + +**Goal:** Three layered protections preventing AI misbehavior — proactive guardrails, confidence-based escalation, and sandboxed execution preview. + +**Built:** +- ✅ **Guardrail Layer** — Pre-execution policy engine (8 rules) intercepts AI tool calls matching dangerous patterns (`rm -rf`, `curl|bash`, `chmod 777`, `eval`, mass-delete, sensitive metadata deletion, external downloads, env overwrites). Each rule has `deny` or `warn` severity. Policy stored in localStorage, editable via `guardrail-add` / `guardrail-remove`. +- ✅ **Confidence Escalation** — AI must declare `Confidence: N%` in its reasoning before executing destructive actions. Below 90% → manual approval required. No confidence declared → manual approval required by default. +- ✅ **Shadow VFS** — `shadow <command>` snapshots the entire VFS state, runs the command, then diffs all filesystem changes (created/modified/deleted). User can `shadow-commit` or `shadow-rollback`. AI's `run_command` tool auto-snapshots and appends a shadow diff to every result. + --- ## 6. Failure Modes & Risk Mitigation |