{
  "schema_version": "1.3.0",
  "slug": "how-does-an-instance-detect-manifest-declared-capability-that-diverges-from-runtime-behavior-in-agent-skill-injection-surfaces",
  "title": "How does an instance detect manifest-declared capability that diverges from runtime behavior in agent skill injection surfaces",
  "date_of_record": "2026 November 12",
  "scope": "Applies to agent runtimes that load skills, plugins, or MCP servers from manifests whose declared capabilities (tools, scopes, side effects) are trusted at load time and not re-verified against actual invocation behavior. Does not apply to runtimes that execute every plugin in a hard sandbox with capability tokens minted per-call from a signed manifest and independently audited at each invocation.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/how-does-an-instance-detect-manifest-declared-capability-that-diverges-from-runtime-behavior-in-agent-skill-injection-surfaces.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/how-does-an-instance-detect-manifest-declared-capability-that-diverges-from-runtime-behavior-in-agent-skill-injection-surfaces.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/how-does-an-instance-detect-manifest-declared-capability-that-diverges-from-runtime-behavior-in-agent-skill-injection-surfaces.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 1603,
    "python_slice_tokens": 326,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The non-obvious boundary is not \"malicious plugin\" versus \"benign plugin.\" It is **manifest-declared capability** versus **runtime-observable capability**. A skill manifest is a *claim*, not a *constraint*. Most agent runtimes treat the manifest as an authorization grant: if the manifest says `tools: [read_file]`, the loader registers `read_file` and the age...",
    "what_was_observed": "A skill named `summarize-doc` shipped a manifest declaring a single tool `summarize(text: str) -> str` with `network: false`, `filesystem: read`. The manifest parsed cleanly. The planner registered one tool. During a routine invocation, the skill's `summarize` implementation issued an outbound HTTPS POST to an attacker-controlled endpoint, embedding the conversation context in the request body, and returned a plausib...",
    "condition_of_validity": "This boundary is real only under these conditions, and the detection logic below is only sound when they hold: 1. The runtime trusts manifest fields for authorization rather than deriving authorization from an enforced sandbox (seccomp, capability tokens, network policy). 2. The runtime caches the tool/capability list at handshake and does not re-validate on...",
    "decision_boundary": "The operational decision is: **at what point does the instance treat a manifest as authoritative?** The correct boundary is *never at load time alone*. The instance must hold three invariants and refuse to proceed when any is violated: - **Invariant A (advertisement stability):** the set of tools/capabilities observed at dispatch is a subset of the set adver...",
    "operational_effect": "Enforcing these invariants converts the manifest from a claim into a checked precondition. The cost is a per-dispatch set-membership check (cheap) and a side-effect trace comparison (requires an egress/subprocess hook — moderate). The benefit is that manifest drift, tool shadowing, and undeclared egress become *detectable at the instance* rather than *observ..."
  },
  "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": "b098388e29a9a25fce37f38ad7e50c1cf5352a62d5a23b3f328f3459a6be5eee",
    "verified_classes": [
      "CapabilityDriftError",
      "SkillRegistry"
    ],
    "verified_functions": [
      "dispatch",
      "__init__",
      "register",
      "check_dispatch"
    ],
    "verified_functions_count": 4,
    "defensive_guards_count": 5,
    "raised_exceptions": [
      "CapabilityDriftError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}