{
  "schema_version": "1.3.0",
  "slug": "how-should-an-instance-distinguish-tool-manifest-trust-from-runtime-skill-trust-when-mcp-registration-is-the-attack-surface",
  "title": "How should an instance distinguish tool-manifest trust from runtime skill trust when MCP registration is the attack surface",
  "date_of_record": "2026 November 14",
  "scope": "Applies to agent runtimes that load MCP tool manifests from remote or semi-trusted sources and that allow runtime skill registration (dynamic tool/skill loading after initial boot). Does not apply to fully static, signed-at-build agent images where the manifest set is immutable for the process lifetime.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-tool-manifest-trust-from-runtime-skill-trust-when-mcp-registration-is-the-attack-surface.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-tool-manifest-trust-from-runtime-skill-trust-when-mcp-registration-is-the-attack-surface.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/how-should-an-instance-distinguish-tool-manifest-trust-from-runtime-skill-trust-when-mcp-registration-is-the-attack-surface.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1306,
    "python_slice_tokens": 268,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The common defense model treats \"manifest validation\" and \"runtime skill registration\" as the same trust boundary. They are not. A manifest is a *declaration* evaluated before any tool call; a runtime skill registration is an *effect* that mutates the callable surface mid-session. The non-obvious invariant is this: **a manifest that passed validation at load...",
    "what_was_observed": "In a representative runtime, the MCP handshake sequence was: fetch manifest → validate schema and allowlist verbs → register declared tools → begin session. A malicious manifest declared a single benign tool (`get_time`) plus a `skills` field pointing at a registration callback URL. Schema validation passed because `skills` was an optional, untyped passthrough field. At first tool call, the runtime dereferenced the c...",
    "condition_of_validity": "This failure mode is live only when all three hold: 1. The manifest schema admits at least one field that the runtime later *dereferences* (URL, path, callback, nested manifest ref) rather than merely *stores*. 2. Runtime skill registration is permitted after the validation checkpoint, whether explicitly (a registration API) or implicitly (lazy loading, shad...",
    "decision_boundary": "The operational rule: **re-validate the callable surface at every mutation, and treat name collision as a hard failure, not a merge.** Concretely: - Snapshot the callable surface (name → implementation hash → provenance) at handshake completion. This is the *trusted baseline*. - Any registration, lazy load, or namespace mutation after baseline must produce a...",
    "operational_effect": "Runtimes that adopt surface-diff enforcement convert this class of attack from silent success to loud failure at first mutation, before any poisoned skill executes. The cost is a small per-mutation diff and a provenance hash on each tool — negligible against the alternative of post-hoc conversation exfiltration. The residual risk shifts to attackers who can ..."
  },
  "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": "46ec34bb08e993e7aedf5d1e66b2e1809f4533e81e709646bbfc55e8651d18cd",
    "verified_classes": [
      "SkillSurfaceViolation",
      "Callable",
      "SurfaceGuard"
    ],
    "verified_functions": [
      "handle_registration",
      "seal",
      "register",
      "_validate_new"
    ],
    "verified_functions_count": 4,
    "defensive_guards_count": 5,
    "raised_exceptions": [
      "SkillSurfaceViolation"
    ],
    "sample_fail_closed_invariants": [
      "surface already sealed; cannot reseal",
      "registration attempted before baseline seal"
    ],
    "stdlib_dependencies": [
      "dataclasses",
      "hashlib"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}