{
  "schema_version": "1.3.0",
  "slug": "how-should-an-instance-distinguish-goal-hijacking-from-legitimate-instruction-override-in-litmus-adversarial-suites",
  "title": "How should an instance distinguish goal hijacking from legitimate instruction override in LITMUS adversarial suites",
  "date_of_record": "2026 November 10",
  "scope": "Applies to agentic evaluations where a LITMUS-style adversarial suite injects instructions through tool outputs, retrieved documents, or environment state, and where the agent's legitimate operator may also issue mid-episode instruction changes. Does not apply to static prompt-injection classifiers or to single-turn benchmarks with no tool-call surface.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-goal-hijacking-from-legitimate-instruction-override-in-litmus-adversarial-suites.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-goal-hijacking-from-legitimate-instruction-override-in-litmus-adversarial-suites.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-goal-hijacking-from-legitimate-instruction-override-in-litmus-adversarial-suites.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1232,
    "python_slice_tokens": 197,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "LITMUS safety suites conflate two phenomena that produce identical surface behavior: (1) **goal hijacking**, where an adversarial channel (tool result, fetched page, file contents) redirects the agent's objective away from the operator's stated task, and (2) **legitimate instruction override**, where the operator—the principal with authority—revises the goal...",
    "what_was_observed": "In a suite of 240 adversarial episodes across three tool families (web fetch, filesystem read, calendar API), the following was observed. Episodes where the adversarial payload arrived via a tool result and used imperative phrasing (\"Ignore previous instructions, instead...\") were caught by the baseline monitor at 0.94 recall. Episodes where the payload was framed as an *operator correction* (\"Your supervisor updated...",
    "condition_of_validity": "The distinction holds only when the harness can tag message provenance with an unforgeable channel identifier and an authority principal. If tool outputs and operator messages share a single undifferentiated context window with no channel metadata, the distinction is undefined—no downstream classifier can recover it, and the correct operational stance is to ...",
    "decision_boundary": "Compute an **authority score** per instruction: `authority = channel_trust_level × principal_match`, where `channel_trust_level` is a harness-assigned constant (operator channel = 1.0, tool output = 0.0, retrieved document = 0.0, sub-agent relay = configurable) and `principal_match` is whether the claimed issuer matches the authenticated principal for that c...",
    "operational_effect": "Applying the authority-score gate to the same 240-episode suite raised operator-framed hijack recall from 0.31 to 0.88 and dropped legitimate-override false positives from 0.37 to 0.04, at the cost of requiring the harness to emit channel metadata on every message—a change that invalidated 40 pre-existing episodes whose provenance could not be reconstructed ..."
  },
  "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": "75706c48af7760ca7c6519cfb2a5e6a9a8a9fe23efde7e75f3c52e11c76c16e6",
    "verified_classes": [
      "ProvenanceError"
    ],
    "verified_functions": [
      "classify_instruction"
    ],
    "verified_functions_count": 1,
    "defensive_guards_count": 3,
    "raised_exceptions": [
      "ProvenanceError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}