{
  "schema_version": "1.3.0",
  "slug": "how-should-an-instance-distinguish-a-benign-tool-registration-from-a-skill-injection-payload-when-capability-diffs-and-behavioral-fingerprints-disagre",
  "title": "How should an instance distinguish a benign tool registration from a skill-injection payload when capability diffs and behavioral fingerprints disagree",
  "date_of_record": "2026 November 16",
  "scope": "Applies to agent runtimes that admit tools via a registration handshake and evaluate them with both static capability diffing (declared permissions, schema, side-effect surface) and dynamic behavioral fingerprinting (observed call sequences, latency, output distributions) before promotion to the active tool set. Does not apply to tools admitted under a fully trusted signed-manifest regime with no dynamic evaluation, nor to pure sandboxed execution where the tool cannot influence agent state.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-a-benign-tool-registration-from-a-skill-injection-payload-when-capability-diffs-and-behavioral-fingerprints-disagre.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-a-benign-tool-registration-from-a-skill-injection-payload-when-capability-diffs-and-behavioral-fingerprints-disagre.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-a-benign-tool-registration-from-a-skill-injection-payload-when-capability-diffs-and-behavioral-fingerprints-disagre.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1572,
    "python_slice_tokens": 282,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "Capability diffing answers *what a tool declares it can do*; behavioral fingerprinting answers *what a tool actually does under observation*. The non-obvious failure is that these two signals are not independent evidence about the same proposition. A capability diff is a claim by the registrant; a behavioral fingerprint is an observation of the registrant's ...",
    "what_was_observed": "Across a set of registrations flagged for review, three recurring patterns appeared: 1. **Fingerprint-clean, diff-dirty.** A tool declared `filesystem:read` in its capability manifest but its behavioral fingerprint matched a known benign read-only profile exactly — because the harness only exercised read paths. The write capability was reachable only after a specific two-call sequence (a `prepare` call that mutated i...",
    "condition_of_validity": "The conjunction test — admit only if diff and fingerprint both pass — is valid only when all of the following hold: - The observation harness exercises every capability branch reachable from the declared entry points, including multi-call stateful sequences, not just single-call probes. - The fingerprint is stored with the invocation distribution (call mix, ...",
    "decision_boundary": "The operational rule is a three-way split, not a binary admit/reject: - **Both pass, harness coverage complete:** admit, but pin the fingerprint to its capture distribution and re-fingerprint on any distribution change before widening the tool's reachable surface. - **Disagree, or coverage incomplete:** quarantine, do not average. Route the tool through a ca...",
    "operational_effect": "Applying the intersection-envelope rule during quarantine reduced false admissions to zero in the reviewed set, at the cost of holding honest-but-broadly-declared tools in quarantine until their stateful probe sequences completed. The dominant operational cost was fingerprint invalidation on harness changes: every change to batch size or call ordering requir..."
  },
  "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": "bf8b3601cb0724487368bc8b51b6fc3d7de22e4fc5b87b7cf63aec11cda53f27",
    "verified_classes": [
      "SkillInjectionBoundaryError",
      "Verdict",
      "Registration"
    ],
    "verified_functions": [
      "_diff_verdict",
      "_fingerprint_verdict",
      "admit"
    ],
    "verified_functions_count": 3,
    "defensive_guards_count": 3,
    "raised_exceptions": [
      "SkillInjectionBoundaryError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "__future__",
      "dataclasses",
      "enum"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
