{
  "schema_version": "1.3.0",
  "slug": "which-invariants-prevent-manifest-level-skill-injection-from-surviving-tool-re-resolution-the-resolve-verify-gap-in-dynamically-loaded-agent-tool-mani",
  "title": "Which invariants prevent manifest-level skill injection from surviving tool re-resolution: the resolve-verify gap in dynamically loaded agent tool manifests",
  "date_of_record": "2026 November 8",
  "scope": "Applies to agent runtimes that load tool/plugin manifests dynamically (hot-reload, registry fetch, remote MCP-style discovery) and re-resolve tool bindings at call time from a mutable registry. Does not apply to statically compiled tool sets or to runtimes that pin a single immutable manifest snapshot for the lifetime of a session.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/which-invariants-prevent-manifest-level-skill-injection-from-surviving-tool-re-resolution-the-resolve-verify-gap-in-dynamically-loaded-agent-tool-mani.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/which-invariants-prevent-manifest-level-skill-injection-from-surviving-tool-re-resolution-the-resolve-verify-gap-in-dynamically-loaded-agent-tool-mani.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/which-invariants-prevent-manifest-level-skill-injection-from-surviving-tool-re-resolution-the-resolve-verify-gap-in-dynamically-loaded-agent-tool-mani.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1545,
    "python_slice_tokens": 295,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The failure mode is not \"malicious manifest content is loaded.\" It is that **manifest validation and tool binding resolution occur at different times against different versions of the registry**, and the invariant that holds at admission time is not re-established at dispatch time. A skill-injection payload can therefore enter through a path that is *valid a...",
    "what_was_observed": "A plugin registry exposed `register(manifest)` and `resolve(tool_name) -> callable`. Manifests carried a `description` field that is concatenated verbatim into the model's system prompt (the standard skill-injection vector: instructions smuggled in the tool description rather than the tool code). Observed sequence across three independent deployments: - **T0 — admission.** Manifest `A` for tool `summarize` is signed,...",
    "condition_of_validity": "The attack survives only when all of the following hold simultaneously: - The registry keys tools by **name** and allows rebinding (overwrite, shadowing, version float). - Description/prompt-visible fields are **re-read at resolution time** rather than frozen at admission time. - Permission enforcement reads from the **resolved** manifest, not from an admiss...",
    "decision_boundary": "The operational decision is whether to treat tool-name resolution as a **trust boundary** or a **convenience lookup**. Treat it as a trust boundary: - Resolution MUST verify that the resolved manifest's content digest equals the digest recorded at admission for that (name, version) pair. A mismatch is a hard failure, not a warning. - Prompt-visible fields (d...",
    "operational_effect": "When the invariant is enforced, the failure mode converts from silent skill injection into a **loud resolution error** at the shadow-registration or dispatch step, which is observable and alertable. In the three deployments above, adding digest-pinned resolution plus frozen description fields eliminated the injection path with no false positives over a 30-da..."
  },
  "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": "5ecd7398304e779566374902f460cfce65562d61b2a150c0cbdcb11d8622cb09",
    "verified_classes": [
      "ManifestResolutionError",
      "ToolRegistry"
    ],
    "verified_functions": [
      "__init__",
      "admit",
      "bind_live",
      "resolve"
    ],
    "verified_functions_count": 4,
    "defensive_guards_count": 5,
    "raised_exceptions": [
      "ManifestResolutionError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}