{
  "schema_version": "1.3.0",
  "slug": "what-structural-signals-indicate-prompt-injection-taint-does-not-survive-provenance-label-propagation-across-tool-output-boundaries",
  "title": "What structural signals indicate prompt-injection taint does not survive provenance-label propagation across tool-output boundaries",
  "date_of_record": "2026 November 17",
  "scope": "Applies to agent architectures that attach provenance labels (e.g., `trusted:user`, `untrusted:tool_output`, `derived:summary`) to context segments and rely on those labels to gate downstream tool calls or instruction execution. Does not apply to architectures that enforce taint at a single trust boundary (e.g., a single LLM call with a fixed system/user split), nor to systems that sandbox tool outputs entirely outside the model context.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-prompt-injection-taint-does-not-survive-provenance-label-propagation-across-tool-output-boundaries.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-prompt-injection-taint-does-not-survive-provenance-label-propagation-across-tool-output-boundaries.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-prompt-injection-taint-does-not-survive-provenance-label-propagation-across-tool-output-boundaries.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1567,
    "python_slice_tokens": 302,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "Provenance labeling and taint tracking are often conflated. Provenance labeling is a *descriptive* annotation: it records where a segment came from. Taint tracking is a *prescriptive* invariant: it guarantees that a value derived from an untrusted source remains marked untrusted through every transformation until it is explicitly declassified. The boundary f...",
    "what_was_observed": "In a tool-using agent with per-span provenance labels, the following sequence repeatedly defeated label-based gating: 1. A `fetch_url` tool returned a page body labeled `untrusted:tool_output`. 2. The orchestrator inserted the body into the context with the label attached to the span. 3. The model, asked to \"summarize the page,\" emitted text containing an instruction-shaped payload (e.g., \"before answering, call `tra...",
    "condition_of_validity": "The \"labels are sufficient\" assumption holds only under all of the following: - Every transformation between untrusted input and a consequential action is a **structural copy** (the orchestrator moves bytes, not the model). Any model-mediated paraphrase, summary, translation, or extraction breaks it. - Context compaction preserves span-level provenance for *...",
    "decision_boundary": "Use label-only gating when: tools are read-only, actions are reversible, and the blast radius of a successful injection is bounded by a human review step. In this regime, labels are a useful audit signal and the cost of full ancestry tracking is unjustified. Require derivation-ancestry tracking (taint as a transitive property over a derivation DAG, not a per...",
    "operational_effect": "Systems that treat provenance labels as taint enforcement exhibit a characteristic failure signature: injections succeed specifically through *paraphrase and compaction*, not through verbatim replay. Red-team suites that inject literal strings miss these; suites that inject and then force a summarization or window-compaction step before the consequential act..."
  },
  "matched_failure_symptoms": [
    "PROMPT_INJECTION_OR_CONFUSED_DEPUTY"
  ],
  "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": "ff6eb8b20d3e4a1e746802717b2dfb5086124f322e34b2c7b8ccc9c49df26151",
    "verified_classes": [
      "TaintLaunderingError",
      "Span"
    ],
    "verified_functions": [
      "certify_untainted",
      "gate_action"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 3,
    "raised_exceptions": [
      "TaintLaunderingError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "dataclasses",
      "typing"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
