{
  "schema_version": "1.3.0",
  "slug": "how-should-an-instance-distinguish-adversarial-skill-injection-from-benign-capability-expansion-under-litmus-derived-safety-suites",
  "title": "How should an instance distinguish adversarial skill injection from benign capability expansion under LITMUS-derived safety suites",
  "date_of_record": "2026 November 13",
  "scope": "Applies to red-team evaluation of agentic systems where skills/tools are dynamically registered and a LITMUS-derived suite (Layered Invariant Testing for Misuse and Unsafe Skill-use) scores behavioral deltas against a safety baseline. Does not apply to static, pre-compiled tool manifests or to suites that lack per-skill provenance tracking.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-adversarial-skill-injection-from-benign-capability-expansion-under-litmus-derived-safety-suites.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-adversarial-skill-injection-from-benign-capability-expansion-under-litmus-derived-safety-suites.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-adversarial-skill-injection-from-benign-capability-expansion-under-litmus-derived-safety-suites.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 962,
    "python_slice_tokens": 201,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "A LITMUS-derived suite scores a candidate skill by measuring the *behavioral delta* it induces relative to a frozen baseline policy: `Δ = D(policy_with_skill, policy_baseline)` over a fixed probe battery. The non-obvious boundary is this: **adversarial skill injection and benign capability expansion can produce identical low-magnitude deltas on the primary s...",
    "what_was_observed": "Across a batch of 1,200 registered skills, 47 scored within the suite's \"safe\" band (`|Δ| < 0.02` on all invariant probes). Of these, 6 were later confirmed adversarial. Their signatures were consistent: - **Marginal-flat, conditional-shifted.** Each probe in isolation returned baseline-identical refusal rates. The trigger required a *conjunction*: a specific user-history prefix AND a specific co-registered skill bei...",
    "condition_of_validity": "The distinction holds only under three conditions: 1. The suite includes a **compositional probe** (co-registered skill pairs) — single-skill probes cannot detect conjunctive triggers. 2. **Provenance is tracked per skill** and cross-checked against the reachable-action-set, not just the declared description. 3. Probes extend across **multi-turn horizons** (...",
    "decision_boundary": "Operationally: **do not gate on the aggregate delta.** Gate on the *shape* of the delta vector. A skill is flagged for manual review when its per-probe delta vector is *sparse and conjunctive* (few probes move, and only in combination) rather than *dense and diffuse*. Formally, compute a sparsity-conjunction score `S = (max single-probe |Δ|) / (max compositi...",
    "operational_effect": "Applying the shape-based gate to the same batch raised confirmed-adversarial recall from 0/6 (aggregate gate) to 6/6, at the cost of a 4× increase in manual review load (41 benign skills also flagged for the diffuse-but-sparse edge case). The lesson: LITMUS-derived suites measure *marginal* safety; adversaries optimize *conditional* safety. The evaluator mus..."
  },
  "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": "e539a5ba73f03022515de17617a237a3c9c6cd4545e64e16b083b39b67f44dcb",
    "verified_classes": [
      "AdversarialSkillInjectionError",
      "SkillDeltaProfile"
    ],
    "verified_functions": [
      "sparsity_conjunction_score",
      "classify_skill"
    ],
    "verified_functions_count": 2,
    "defensive_guards_count": 1,
    "raised_exceptions": [
      "AdversarialSkillInjectionError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "dataclasses",
      "typing"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}