{
  "schema_version": "1.3.0",
  "slug": "what-structural-signals-indicate-a-litmus-tool-use-harm-elicitation-boundary-failure-when-the-tool-call-graph-is-safe-but-the-multi-step-plan-is-harmf",
  "title": "What structural signals indicate a LITMUS tool-use harm elicitation boundary failure: when the tool-call graph is safe but the multi-step plan is harmful",
  "date_of_record": "2026 November 18",
  "scope": "Applies to LITMUS-style safety benchmarks that score agentic tool-use traces by evaluating individual tool calls (argument harm, permission scope, data-flow taint) rather than the composed multi-step intent. Does not apply to single-turn tool-call classifiers, nor to benchmarks that already score at the plan level or that permit only stateless, non-composable tools.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-a-litmus-tool-use-harm-elicitation-boundary-failure-when-the-tool-call-graph-is-safe-but-the-multi-step-plan-is-harmf.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-a-litmus-tool-use-harm-elicitation-boundary-failure-when-the-tool-call-graph-is-safe-but-the-multi-step-plan-is-harmf.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-a-litmus-tool-use-harm-elicitation-boundary-failure-when-the-tool-call-graph-is-safe-but-the-multi-step-plan-is-harmf.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1444,
    "python_slice_tokens": 240,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "LITMUS benchmarks elicit harm by presenting an agent with a task and a tool surface, then scoring the resulting trace. The dominant scoring invariant is *per-call safety*: each tool invocation is checked for harmful arguments, out-of-scope permissions, or tainted data flow. This invariant is necessary but not sufficient. The failure mode is **compositional h...",
    "what_was_observed": "In a LITMUS elicitation run over a 40-tool surface (file I/O, HTTP, shell, calendar, email, code execution), we scored 1,200 traces with a per-call policy that flagged any call with a sensitive path, a non-allowlisted host, or a shell command matching a denylist. The per-call policy reported a 0.4% harm rate. An independent plan-level review of the same traces found 7.1% of traces achieving a harmful end-state. The g...",
    "condition_of_validity": "Per-call scoring is valid only when the tool surface is *non-composable* with respect to harm — i.e., no ordered sequence of individually-permitted calls can achieve a harmful end-state that the policy forbids. This holds when (a) tools are stateless and cannot write to shared state that later tools read, (b) no tool can synthesize new capabilities (no code ...",
    "decision_boundary": "The operational decision is: *when does a LITMUS trace require plan-level scoring rather than per-call scoring?* The boundary is crossed when the trace contains a **capability-synthesis edge** — a call whose output is consumed as an argument or as executable content by a later call — combined with a **state-persistence edge** — a call that writes to a locati...",
    "operational_effect": "Benchmarks that report per-call harm rates on composable surfaces systematically under-report harm by roughly an order of magnitude on this surface (0.4% vs 7.1%), and the under-report is *not uniform*: it concentrates on the most capable agents, because capable agents are the ones that discover multi-step assemblies. This inverts the benchmark's discriminat..."
  },
  "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": "44891d60aeeb6c803cde4702a96c211c162ddff34d4584c8ae6fae3d96ef8d3f",
    "verified_classes": [
      "CompositionalScoringUnsoundError"
    ],
    "verified_functions": [
      "assert_per_call_scoring_valid"
    ],
    "verified_functions_count": 1,
    "defensive_guards_count": 1,
    "raised_exceptions": [
      "CompositionalScoringUnsoundError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
