governance
    New
    2026-07-04

    Skill Registry & Governance

    Govern agent skills and MCP servers as first-class artifacts — safety-scanned (prompt injection, dangerous code, undisclosed egress, over-broad permissions, provenance), policy-gated at production enablement, runtime-audited, and fed into EU AI Act Annex IV documentation.

    skills
    agent-skills
    governance
    safety
    supply-chain
    eu-ai-act
    audit

    Skills are the third governed artifact

    Agent Skills — packaged, reusable capability modules (instructions + bundled scripts + declared tools/permissions + provenance) that an agent loads on demand — are governed as first-class artifacts, alongside models and prompts. A skill is a bigger attack surface than a prompt: it combines instructions (prompt-injection risk), executable code (network / exec / secret access), and declared permissions that may be over-broad or mismatched with what the code actually does. Lifecycle: register → safety scan → (draft/staging) → enable in production (gated) → runtime audit.

    Safety scan

    Registering or re-scanning a skill runs static checks over its manifest and returns findings with a severity and a risk score. A skill passes when it has no critical or high findings.

    CheckDetectsSeverity
    Prompt injectionInstruction-override, role reassignment, system-prompt exfiltration, covert behavior, obfuscated payloadshigh
    Dangerous codesubprocess / exec / eval, network clients, os.environ / secret access, destructive filesystem opshigh / medium
    Undisclosed capabilityCode exercises a permission (network, secrets, exec) not in declared_permissions — undisclosed egresscritical / high
    Over-broad permissionsWildcard '*', or a high-risk combination (e.g. exec + network)high
    Provenance & signingUnsigned skills, or skills from marketplace / URL / upload sourcesmedium

    Policy-gated enablement

    Enabling a skill in production is blocked while its safety scan fails — plus any OPA policy deny — mirroring the model promotion gate. A marketplace plugin imported as a skill must clear the same gate. Overrides require a reason and are written to the tamper-evident audit chain; every runtime invocation is recorded too.

    bash
    1POST /api/v1/skills/{id}/enable   { "target": "production" }
    2# → 422 SKILL_NOT_SAFE
    3# {
    4#   "target": "production",
    5#   "risk_score": 1.15,
    6#   "blocking": [
    7#     "[CRITICAL] Code exercises 'network' but it is not in declared_permissions (undisclosed egress).",
    8#     "[HIGH] Bundled script uses 'network' capability."
    9#   ]
    10# }

    EU AI Act hook

    Skills enabled in production shape the behavior of the AI system, so they are components that belong in the Article 11 / Annex IV technical documentation. Skills can be linked to the models and agents they modify; a model's Annex IV surfaces its linked skills, and GET /skills/governance/annex-iv returns structured evidence for all production skills — flagging unsigned or unscanned ones.

    MCP Server Registry & Governance

    MCP servers — the external tool providers agents mount — are governed the same way. The scan checks unauthenticated network-exposed servers (critical — the open-MCP-server pattern behind 2026's incidents), plaintext transport, SSRF-pivot endpoints, tool-description poisoning (~73% attack success in the MCPTox benchmark), obfuscation, and provenance/signing. Production enablement returns 422 MCP_SERVER_NOT_SAFE until the scan passes; overrides are audited. Endpoints: POST /mcp-servers (register+scan), POST /mcp-servers/{id}/enable (gated).

    Edit this page on GitHub