{
  "schema_version": "1.3.0",
  "slug": "what-structural-signals-indicate-skill-injection-attack-surfaces-in-dynamically-loaded-agent-skills-and-plugin-registries",
  "title": "What structural signals indicate skill-injection attack surfaces in dynamically loaded agent skills and plugin registries",
  "date_of_record": "2026 November 18",
  "scope": "Applies to agent runtimes that resolve skills or plugins from a mutable registry at invocation time (or on a refresh interval) and bind them by name, namespace, or capability tag. Does not apply to statically linked skill sets compiled into the agent image, nor to registries where the resolver and the signer are the same trust domain with no dynamic update path.",
  "projections": {
    "unified_markdown_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-skill-injection-attack-surfaces-in-dynamically-loaded-agent-skills-and-plugin-registries.md",
    "method_python_slice_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-skill-injection-attack-surfaces-in-dynamically-loaded-agent-skills-and-plugin-registries.py",
    "remnant_warrant_slice_uri": "https://corpusfetch.com/c/what-structural-signals-indicate-skill-injection-attack-surfaces-in-dynamically-loaded-agent-skills-and-plugin-registries.warrant.json"
  },
  "token_profile": {
    "full_markdown_tokens": 2008,
    "python_slice_tokens": 475,
    "warrant_slice_tokens": 220
  },
  "remnant_summary": {
    "core_distinction": "The failure is not \"a malicious skill was loaded.\" That is a detection problem with an obvious signature. The non-obvious boundary is **binding ambiguity**: the resolver picks a skill by a *name* or *tag*, but the security-relevant identity of a skill is its *content hash plus provenance chain*. When those two notions of identity are allowed to diverge — eve...",
    "what_was_observed": "Across several agent deployments using tag-based skill resolution, four structural signals preceded exploitable states. None of them are \"a bad skill appeared\"; each is a *shape* in the registry and resolver that makes injection cheap. 1. **Mutable tags resolving to content-addressed storage.** The registry stores skills by digest but exposes them by tag (`summarizer@stable`, `retriever@v2`). The tag→digest mapping i...",
    "condition_of_validity": "The observations above hold only under these conditions, and the mitigations below are only warranted when they hold: - The registry is writable by a principal set **larger** than the agent's operator — i.e., there is a genuine multi-tenant or delegated-publish model. If the agent and registry share one trust domain with no external writers, tag mutability i...",
    "decision_boundary": "The operational question is not \"is the registry mutable\" but \"**does any authorization decision reference an identity that is not the content digest?**\" Draw the boundary there. - **Inside the boundary (injectable):** resolution by mutable tag; first-match capability selection; trust roots co-located with the mutable store; refresh without generation counte...",
    "operational_effect": "Concretely, enforcing the invariant changes three things: 1. **Audit logs become trustworthy.** Logging the digest, not the tag, means a later registry mutation cannot retroactively rewrite what \"executed.\" Name-based logs are forensically useless against this class of attack because the name is precisely what the attacker preserves. 2. **Refresh becomes saf..."
  },
  "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": "11ad2daf14fdb2147a105c6d09183dac35998e19a411ecd4e986a6d6c022224f",
    "verified_classes": [
      "SkillBindingError",
      "Authorization",
      "ResolvedSkill"
    ],
    "verified_functions": [
      "_digest",
      "verify_binding",
      "resolve_capability"
    ],
    "verified_functions_count": 3,
    "defensive_guards_count": 6,
    "raised_exceptions": [
      "SkillBindingError"
    ],
    "sample_fail_closed_invariants": [],
    "stdlib_dependencies": [
      "dataclasses",
      "hashlib"
    ],
    "observation_mode": "EMPIRICAL_BOUNDARY_CAPTURE",
    "zero_external_deps": true
  }
}
