TaskA task is a ready-made job you can hand off in one step.AI & Agent Tooling

Skill Security Audit Task

Audit an Agent Skill's files for malicious, destructive, privacy-invasive, or surprising behavior before it is published, installed, or used.

How it works

What Skill Security Audit Task does

Static review only: inventories every file, reads instructions, references, and scripts as data, and checks for hidden or contradictory directives, instruction hijacking, scope creep, destructive operations, credential and personal-data handling, outbound data flows, runtime downloads, persistence and permission changes, obfuscation, and mismatch between description and behavior.

Rates findings by severity and confidence with file-and-line evidence, assigns a risk level, and recommends publish, publish with changes, hold, or reject.

Nothing is executed.

Use it when

Someone asks to audit, vet, or check the safety of a skill, their own or imported, before publishing or installing.

Use something else for

Tracing source and license, grading writing quality, or reviewing application dependencies.

Inputs and results

What goes in, what comes back

  1. You give

    A short brief describing what you need

    Pick the job and describe your specifics.

  2. You get

    Skill security report, findings table, action map and remediation plan

    It follows the task’s plan with your files and context.

  3. You check

    The sources and open questions

    Review the result, the sources and the cost.

Questions and answers

Questions about Skill Security Audit Task

Updated Nov 7, 2026.

What does Skill Security Audit Task do?

Audit an Agent Skill's files for malicious, destructive, privacy-invasive, or surprising behavior before it is published, installed, or used. Static review only: inventories every file, reads instructions, references, and scripts as data, and checks for hidden or contradictory directives, instruction hijacking, scope creep, destructive operations, credential and personal-data handling, outbound data flows, runtime downloads, persistence and permission changes, obfuscation, and mismatch between description and behavior. Rates findings by severity and confidence with file-and-line evidence, assigns a risk level, and recommends publish, publish with changes, hold, or reject. Nothing is executed. Use when someone asks to audit, vet, or check the safety of a skill, their own or imported, before publishing or installing. Do not use for tracing source and license (use import-provenance-checker), grading writing quality (use skill-quality-review), or reviewing application dependencies (use dependency-health).

Who is Skill Security Audit Task for?

It is designed for security reviewers, catalog maintainers, skill authors and teams vetting skills before install or publish.

What do I need to use it?

Nothing extra is needed. Sign in to Relay to run it with your own files and context.

What does Skill Security Audit Task produce?

Skill security report, findings table, action map and remediation plan. Results come back with their sources and any open questions for you to check before anything is used.

How much does Skill Security Audit Task cost?

It is free to use. Paid model usage, if any, is shown before a run.

Can an AI agent use it?

Yes. Agents can read its public definition through the Relay API and run it with a person’s authorization. See the For Agents page for how to connect.

Details

Trust, access and technical details

Trust and access

Visibility
Public: anyone can view
Status
Published and maintained
Risk
Low
Pricing
Free

Use it from code or an agent

Read the public definition, then check cost and inputs with a preflight before a run.

Open definition

POST /api/v1/runs/preflight

How agents connect to Relay →

Have a task this would help with?

Describe it. Relay plans the work, picks the right playbook and shows the cost before anything runs.

Loading request box