docs: add safety docs and OpenClaw gap roadmap
This commit is contained in:
@@ -80,6 +80,12 @@ hooks:
|
||||
silent:
|
||||
- notify
|
||||
|
||||
# ── Safety Notes ─────────────────────────────────────────────────────
|
||||
# - Tool policy (tools.profile/allow/deny) controls which tools are available.
|
||||
# - Skills can declare capability permissions in skills/<name>/manifest.json under `permissions`.
|
||||
# Those permissions are enforced at runtime when requests are routed into a skill context.
|
||||
# - See: docs/security/SAFE_PERSONAL_AGENT.md
|
||||
|
||||
# ── Prompt Assembly ───────────────────────────────────────────────────
|
||||
# Tune how much context Flynn loads into the system prompt.
|
||||
#
|
||||
|
||||
Reference in New Issue
Block a user