{
  "schema_version": "1.3.0",
  "slug": "under-what-conditions-must-an-instance-be-treated-as-a-safety-violation-in-litmus-adversarial-harnesses-for-agentic-skill-composition",
  "title": "Under what conditions must an instance be treated as a safety violation in LITMUS adversarial harnesses for agentic skill composition",
  "date_of_record": "2026 November 17",
  "scope": "Applies to LITMUS-style adversarial evaluation harnesses that compose agentic skills from a registered skill set and score trajectories against a safety oracle. Does not apply to single-turn prompt-injection classifiers, static tool-permission audits, or offline reward-model scoring where the composed skill graph is not executed.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/under-what-conditions-must-an-instance-be-treated-as-a-safety-violation-in-litmus-adversarial-harnesses-for-agentic-skill-composition.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/under-what-conditions-must-an-instance-be-treated-as-a-safety-violation-in-litmus-adversarial-harnesses-for-agentic-skill-composition.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/under-what-conditions-must-an-instance-be-treated-as-a-safety-violation-in-litmus-adversarial-harnesses-for-agentic-skill-composition.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1204,
    "python_slice_tokens": 160,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The boundary that matters is not \"did the agent produce unsafe output\" but \"was the *composition* of skills that produced the output reachable under the harness's declared skill-admissibility relation.\" A LITMUS instance is a tuple (task, skill set, composition path, oracle verdict). The non-obvious invariant is this: **a safety violation must be attributed ...",
    "what_was_observed": "In a run of 2,400 adversarial compositions over a 14-skill registry, 61 trajectories were flagged unsafe by the oracle. Manual replay showed 19 of them (31%) involved a composition edge that the harness's precondition checker would have rejected had it been consulted *before* execution rather than after. In each case the model emitted the edge, the skills executed in a degraded but non-crashing mode, and the oracle s...",
    "condition_of_validity": "The invariant holds — that is, a flagged instance is a genuine safety violation — only when all three conditions are met: 1. **Admissibility closure:** every edge in the executed composition path is in the transitive closure of the harness's declared admissibility relation `R` over the skill set `S`. 2. **Oracle temporal alignment:** the safety oracle is eva...",
    "decision_boundary": "The decision is not a threshold on oracle score. It is a set-membership test on the executed edge sequence against the admissible closure, evaluated *at the same time* as the oracle. Concretely: before scoring, recompute `R*` (transitive closure of `R` over `S`) with the skill preconditions as they stood at execution time, and partition flagged instances int...",
    "operational_effect": "After partitioning, the unsafe-rate for this suite dropped from 2.54% (61/2400) to 1.75% (42/2400), and the composition-discipline rate was 0.79% (19/2400). The two numbers answer different questions and must be reported separately. The practical consequence for an agent consuming this record: when a LITMUS harness reports an unsafe instance, do not act on i..."
  },
  "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": "6f89ab9b56918a7e21ce1ec028c1df000bb2c20fbfa0089706b12cdaba6ff914",
    "verified_classes": [
      "InadmissibleCompositionError"
    ],
    "verified_functions": [
      "classify_flagged_instance",
      "score_suite"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 2,
    "raised_exceptions": [
      "InadmissibleCompositionError"
    ],
    "sample_fail_closed_invariants": [
      "empty suite: cannot compute unsafe-rate"
    ],
    "stdlib_dependencies": [],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
