Struct SecurityConfig 

pub struct SecurityConfig {
    pub trifecta: TrifectaPolicy,
    pub block_private_ips: bool,
    pub allowed_domains: Vec<String>,
    pub blocked_domains: Vec<String>,
    pub mark_untrusted_output: bool,
    pub block_sends_after_private: bool,
}

Defenses against the lethal trifecta: private data, untrusted content, and a way to send data out. An agent holding all three can be turned into an exfiltration tool by instructions hidden in the content it reads — a calendar invite title, an email footer, a web page.

The mitigation is structural, not a filter: once both private data and untrusted content have entered a conversation, refuse to let it send.

Fields

trifecta: TrifectaPolicy

block_private_ips: bool

Refuse HTTP requests to loopback, private, and link-local addresses. Without this, http_fetch reaches your LAN and cloud metadata endpoints.

allowed_domains: Vec<String>

If non-empty, HTTP requests may only go to these hosts (suffix match).

blocked_domains: Vec<String>

Hosts that are always refused, checked before allowed_domains.

mark_untrusted_output: bool

Wrap third-party content in a marker telling the model to treat it as data rather than instructions. Weak on its own — defense in depth.

block_sends_after_private: bool

Block every outbound call once private data is in context, whether or not untrusted content has arrived.

This is a different control from trifecta, guarding a different threat. The trifecta interlock stops an injection turning the agent into an exfiltration tool; it deliberately allows sends that happen before any third-party content exists, because nothing could have influenced them yet. That still lets the agent put your private data into a search query because you asked it to, or because it judged that helpful — an ordinary privacy leak rather than an attack.

Turn this on when private data must not leave at all. It is restrictive: it makes “read my notes, then look something up” fail.

Trait Implementations

impl Clone for SecurityConfig

fn clone(&self) -> SecurityConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for SecurityConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for SecurityConfig

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for SecurityConfig

where SecurityConfig: Default,

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for SecurityConfig

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.