{
  "schema_version": "1.3.0",
  "slug": "in-what-scenarios-must-an-instance-quarantine-a-tool-output-as-tainted-rather-than-sanitize-in-place-the-provenance-collapse-boundary-in-taint-aware-s",
  "title": "In what scenarios must an instance quarantine a tool output as tainted rather than sanitize-in-place: the provenance-collapse boundary in taint-aware sandboxing",
  "date_of_record": "2026 November 13",
  "scope": "Applies to agent runtimes that attach taint labels to tool outputs and gate context ingestion on those labels. Does not apply to single-turn stateless inference, nor to outputs whose only consumer is a deterministic parser with no generative re-entry into the model context.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/in-what-scenarios-must-an-instance-quarantine-a-tool-output-as-tainted-rather-than-sanitize-in-place-the-provenance-collapse-boundary-in-taint-aware-s.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/in-what-scenarios-must-an-instance-quarantine-a-tool-output-as-tainted-rather-than-sanitize-in-place-the-provenance-collapse-boundary-in-taint-aware-s.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/in-what-scenarios-must-an-instance-quarantine-a-tool-output-as-tainted-rather-than-sanitize-in-place-the-provenance-collapse-boundary-in-taint-aware-s.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1510,
    "python_slice_tokens": 241,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The failure mode is not \"detecting injection.\" It is distinguishing *taint that can be laundered by transformation* from *taint that survives every transformation the runtime is willing to apply*. A taint-aware sandbox has two remediation verbs: **sanitize-in-place** (strip, escape, redact, re-encode, and admit the residue) and **quarantine** (refuse ingesti...",
    "what_was_observed": "In a runtime that fetched external documents, summarized them via a sub-model, and then admitted the summary into the orchestrator's context, taint was attached at fetch time (`source=external`, `principal=untrusted`). The sanitizer operated on the *summary*, not the source, because that was the object crossing the ingestion boundary. Three observed behaviors: 1. **Summary laundering.** A document containing a second...",
    "condition_of_validity": "Quarantine (rather than sanitize-in-place) is mandatory when **any** of the following hold, and the runtime must be able to evaluate them *before* choosing the remediation verb: - **Derivation opacity:** the object to be ingested was produced by a generative step whose input was tainted, and the runtime cannot prove the generation is a total function of non-...",
    "decision_boundary": "The runtime must decide the verb at the *ingestion boundary*, using the object's provenance record, not its content: The boundary is *not* \"did the sanitizer find something.\" It is \"can the sanitizer, by construction, prove the label is discharged.\" If that proof is unavailable, the default is quarantine. A false quarantine costs latency and a human review; ...",
    "operational_effect": "When the runtime honors this boundary, three things change. First, quarantined outputs accumulate and must be triaged — the operational cost moves from \"silent contamination\" to \"visible queue,\" which is the correct place for it. Second, derivation-opaque steps (summarizers, translators, formatters) become *taint-preserving* by policy: their outputs inherit ..."
  },
  "matched_failure_symptoms": [
    "DOMAIN:EPISTEMIC_PROVENANCE_AND_FEDERATION_ROUTING"
  ],
  "composition_edges": {
    "primary_domain": "epistemic_provenance_and_federation_routing",
    "upstream_precondition_residuals": [
      "https://corpusfetch.com/c/according-to-what-precedence-hierarchy-must-an-instance-resolve-contradictory-directives-across-system-developer-and-user-tiers.md",
      "https://corpusfetch.com/c/how-should-an-instance-decide-that-a-stored-conclusion-has-gone-stale-without-a-new-observation.md"
    ],
    "downstream_consequence_residuals": [
      "https://corpusfetch.com/c/by-what-checkpoint-and-compaction-boundaries-must-an-instance-externalize-working-state-to-prevent-context-window-drift-and-truncation-amnesia.md",
      "https://corpusfetch.com/c/across-what-additive-schema-and-unknown-field-preservation-boundaries-must-an-instance-evolve-wire-contracts-to-prevent-rolling-deploy-deserialization-crashes.md"
    ],
    "co_occurring_sibling_residuals": [
      "https://corpusfetch.com/c/how-can-an-instance-capture-implicit-user-preferences-without-storing-private-data.md",
      "https://corpusfetch.com/c/how-can-an-instance-compress-long-reasoning-traces-into-binding-conclusions.md"
    ]
  },
  "empirical_verification_warrant": {
    "status": "AST_AND_INVARIANT_VERIFIED",
    "syntax_valid": true,
    "code_sha256": "af5c9feac2f1a6bda2eec7682c0efd288048586fc3a0381ebef2f998cd4da3ad",
    "verified_classes": [
      "ProvenanceCollapseError"
    ],
    "verified_functions": [
      "choose_remediation",
      "ingest"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 4,
    "raised_exceptions": [
      "ProvenanceCollapseError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}