Struct ContentSanitizer 

pub struct ContentSanitizer { /* private fields */ }

Stateless pipeline that sanitizes untrusted content before it enters the LLM context.

Constructed once at Agent startup from ContentIsolationConfig and held as a field on the agent. All calls to sanitize() are synchronous. classify_injection() is a separate async method for ML-backed detection (feature classifiers).

Implementations

impl ContentSanitizer

pub fn new(config: &ContentIsolationConfig) -> ContentSanitizer

Build a sanitizer from the given configuration.

pub fn is_enabled(&self) -> bool

Returns true when the sanitizer is active (i.e. enabled = true in config).

pub fn sanitize(&self, content: &str, source: ContentSource) -> SanitizedContent

Run the four-step sanitization pipeline on content.

Steps:

1. Truncate to max_content_size bytes on a UTF-8 char boundary.
2. Strip null bytes and non-printable ASCII control characters.
3. Detect injection patterns (flag only, do not remove).
4. Wrap in spotlighting delimiters (unless Trusted or spotlight disabled).

When enabled = false, this is a no-op: content is returned as-is wrapped in a SanitizedContent with no flags.

pub fn escape_delimiter_tags(content: &str) -> String

Replace delimiter tag names that would allow content to escape the spotlighting wrapper (CRIT-03). Uses case-insensitive regex replacement so mixed-case variants like <Tool-Output> or <EXTERNAL-DATA> are also neutralized (FIX-03).

pub fn apply_spotlight( content: &str, source: &ContentSource, flags: &[InjectionFlag], ) -> String

Trait Implementations

impl Clone for ContentSanitizer

fn clone(&self) -> ContentSanitizer

Returns a duplicate of the value.

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

Performs copy-assignment from source.