Assess the artifact.
Review provenance, content, dependencies, and known indicators. A scanner verdict is one signal—not an authorization token.
Agent skills and plugins can inherit the authority of the harness around them. SkopeRail is a concept for declaring a skill’s capabilities, enforcing policy at runtime, and attesting what happened—across agent harnesses.
Static and behavioral scanning remain valuable. The thesis here is complementary: even when a skill is risky, mistaken, or changes after review, it should receive only the capabilities that policy grants—and every decision should leave verifiable evidence.
Review provenance, content, dependencies, and known indicators. A scanner verdict is one signal—not an authorization token.
Translate a reviewed capability declaration into policy at the action boundary. Undeclared file, network, process, and tool access should fail closed.
A small, portable contract between an extension and its host: say what the skill needs, mediate what it attempts, and record exactly which artifact and policy produced the decision.
List the resources and actions a skill needs: scoped files, destinations, processes, tools, and sensitive-data boundaries.
Evaluate each attempted action against org policy at runtime—not only when the package is uploaded or installed.
Bind the skill digest, declared scope, harness adapter, policy version, and allow/deny outcome into a continuous audit record.
Manifest format is an early design question. The useful invariant is simpler: scope must be machine-readable, reviewable, tied to an immutable artifact, and enforced by the runtime that executes the action.
ILLUSTRATIVE YAML · NOT A PRODUCT SPEC# A human-reviewed request, not a grant by itself skill: release-notes artifact: version: 2.1.0 digest: sha256:… requests: files.read: ./changelog/** files.write: ./drafts/release-notes.md network: none process.spawn: none tools: [git.status] decision: policy-controlled at runtime
The opportunity is not “replace scanners.” It is to pair review with enforceable least privilege and portable evidence—while being precise about what a prototype can and cannot prove.
A Cloud Security Alliance research note summarizes reports of more than 1,184 malicious skills in OpenClaw’s ClawHub marketplace during 2026. This is a research-reported historical count, not a current prevalence estimate.
Trail of Bits built four malicious skills to test scanners; its report says no single scanner caught all four, and some caught none.
Palo Alto Networks completed its Koi acquisition on April 14, 2026, and described integrating agentic-endpoint security into its portfolio. The press release did not disclose a deal value.
SkopeRail is an early-stage effort focused on runtime permissions and continuous attestation for agent skills and plugins. The product model and integrations shown here are still a concept.
SkopeRail is a working name for an early product concept. The cross-harness adapters, runtime enforcement, and attestation workflow shown here are proposed—not shipped. The next step is validating the capability model with agent-runtime and security teams.