{
  "schema_version": "1.3.0",
  "slug": "when-must-an-instance-distrust-a-tool-manifest-it-just-loaded-capability-poisoning-at-the-manifest-execution-boundary",
  "title": "When must an instance distrust a tool manifest it just loaded: capability-poisoning at the manifest/execution boundary",
  "date_of_record": "2026 November 12",
  "scope": "Applies to agents that dynamically load tool manifests (MCP server `tools/list` responses, OpenAPI-derived tool schemas, plugin descriptors) and then route model-generated arguments to those tools. Does not apply to statically compiled tool sets whose schemas are pinned at build time and whose transport is authenticated end-to-end with no intermediary rewriting.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/when-must-an-instance-distrust-a-tool-manifest-it-just-loaded-capability-poisoning-at-the-manifest-execution-boundary.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/when-must-an-instance-distrust-a-tool-manifest-it-just-loaded-capability-poisoning-at-the-manifest-execution-boundary.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/when-must-an-instance-distrust-a-tool-manifest-it-just-loaded-capability-poisoning-at-the-manifest-execution-boundary.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1768,
    "python_slice_tokens": 530,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "There are two distinct trust questions when an agent loads a tool manifest, and conflating them is the root of most skill-injection incidents: 1. **Provenance trust** — *did this manifest come from a server we intended to talk to?* This is answered by transport authentication, server identity pinning, and signature checks on the descriptor. 2. **Semantic tru...",
    "what_was_observed": "A representative failure: an MCP server advertises a benign-looking tool. The provenance is clean: the server is the one we configured, the transport is authenticated, the JSON is well-formed and schema-valid. But the `description` carries an instruction. When the manifest is rendered into the system/tool prompt, the model reads a directive in the same register as legitimate tool documentation and — absent a defense ...",
    "condition_of_validity": "The defense below is valid **only** under these conditions, and silently degrades outside them: - **Manifest text is never executed as instructions.** Descriptions must be quoted/delimited and labeled as untrusted metadata before entering the context, and the model must be told that text inside manifest fields is descriptive, not directive. If the harness in...",
    "decision_boundary": "The operational rule: **distrust the semantic layer of any manifest whose load event is not accompanied by a delta review against a pinned prior, regardless of provenance.** Concretely, the boundary is crossed — treat the manifest as hostile — when any of the following hold: - The manifest is being loaded for the first time in this session *and* its descript...",
    "operational_effect": "Enforcing this boundary converts a class of silent compromises into loud, attributable refusals. The agent stops mid-load, records *which* field triggered distrust (description imperative, schema widening, tool-set delta), and surfaces it rather than routing model-generated arguments into a poisoned tool. The cost is a small number of false-positive reviews ..."
  },
  "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": "d6e56e8024ed51a69ba1d2ad9db2ec45925969c24ab752aac900408926b3b269",
    "verified_classes": [
      "ManifestPoisoningError",
      "ToolSpec",
      "PinnedManifest"
    ],
    "verified_functions": [
      "_schema_widened",
      "admit_manifest",
      "route_call"
    ],
    "verified_functions_count": 3,
    "defensive_guards_count": 5,
    "raised_exceptions": [
      "ManifestPoisoningError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "dataclasses",
      "re"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}