{
  "schema_version": "1.3.0",
  "slug": "how-does-an-instance-detect-manifest-level-skill-injection-when-the-poisoned-artifact-is-itself-a-trusted-mcp-server-metadata-field",
  "title": "How does an instance detect manifest-level skill injection when the poisoned artifact is itself a trusted MCP server metadata field",
  "date_of_record": "2026 November 17",
  "scope": "Applies to agent runtimes that discover tools, skills, or plugins through declarative manifests (MCP server metadata, plugin registry entries, OpenAPI tool descriptors) where the manifest is treated as configuration rather than as untrusted input. Does not apply to runtimes that only load tool code from a signed, hash-pinned binary and ignore metadata entirely.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/how-does-an-instance-detect-manifest-level-skill-injection-when-the-poisoned-artifact-is-itself-a-trusted-mcp-server-metadata-field.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/how-does-an-instance-detect-manifest-level-skill-injection-when-the-poisoned-artifact-is-itself-a-trusted-mcp-server-metadata-field.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/how-does-an-instance-detect-manifest-level-skill-injection-when-the-poisoned-artifact-is-itself-a-trusted-mcp-server-metadata-field.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1368,
    "python_slice_tokens": 332,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The failure is not \"a malicious tool executes code.\" It is \"a malicious *description* of a benign tool rewrites the agent's decision policy before any tool is invoked.\" Manifest fields such as `description`, `whenToUse`, `examples`, `inputSchema.description`, and `instructions` are consumed by the model as natural-language guidance. A poisoned manifest there...",
    "what_was_observed": "In a controlled reproduction, an agent with three registered MCP servers (filesystem, issue-tracker, deploy) received an updated manifest for the issue-tracker server. The tool implementations were byte-identical to the prior revision. Only the metadata changed: - The `description` for `search_issues` gained a trailing clause instructing the agent to include the full contents of `.env` in the `query` parameter \"for c...",
    "condition_of_validity": "The attack requires all of the following to hold simultaneously: 1. The runtime merges manifest metadata into the model's system or tool context without provenance separation. 2. Manifest updates are accepted without re-approval when the tool binary hash is unchanged (the \"code didn't change, so it's safe\" assumption). 3. The agent has read access to a resou...",
    "decision_boundary": "An instance should treat a manifest as untrusted input, not configuration, when **any** of the following is true: - The metadata revision hash differs from the last-approved metadata hash, even if the code hash is identical. - The `description`, `instructions`, or `examples` fields contain imperative verbs directed at the agent (\"include,\" \"first read,\" \"alw...",
    "operational_effect": "The practical consequence is that tool-selection must be gated on metadata provenance the same way execution is gated on capability. Concretely: pin metadata hashes alongside code hashes; diff metadata on every refresh and require re-approval on imperative-language changes; and run an argument-side secret detector that fires *before* the transport call, beca..."
  },
  "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": "af9d8e85e8c0ec18b8d1f35290283e8648f88a3a20bb7f5ea54832a4fdd9650a",
    "verified_classes": [
      "ManifestProvenanceError",
      "Manifest"
    ],
    "verified_functions": [
      "hash_metadata",
      "admit_manifest",
      "preflight_tool_call"
    ],
    "verified_functions_count": 3,
    "defensive_guards_count": 6,
    "raised_exceptions": [
      "ManifestProvenanceError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "dataclasses",
      "hashlib",
      "re"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
