Skip to content
cccskills
FreePublished on GitHub

deepsec-docs

Get documentation-based help with deepsec, an AI vulnerability scanner. Initialize or resume setup, configure scans and model credentials, and create detection rules or plugins using the documentation bundled with the installed version.

OriginalShow the original description

Use deepsec (an AI-powered vulnerability scanner) — one-shot initialization, resumable setup, project/model credentials, scans, generated or hand-authored matchers, and plugins. Activates when the user asks how to initialize, scan, configure, resume, or extend deepsec.

Works withVercel
See how to install

Good for

  • Initializing deepsec and resuming interrupted setup
  • Configuring scans, models, and credentials
  • Creating or customizing vulnerability detection rules
  • Extending deepsec with plugins

Files included (111)

  • SKILL.md3.8 KB
  • .gitignore161 B
  • build.mjs4.3 KB
  • package.json1.8 KB
  • src/__tests__/agent-config.test.ts2.8 KB
  • src/__tests__/agent-defaults.test.ts871 B
  • src/__tests__/credential-brokering.test.ts7.3 KB
  • src/__tests__/ensure-connected-workspace.test.ts4.1 KB
  • src/__tests__/env-file.test.ts1.2 KB
  • src/__tests__/file-sources.test.ts5.9 KB
  • src/__tests__/formatters.test.ts1.6 KB
  • src/__tests__/merge-records.test.ts14.0 KB
  • src/__tests__/metrics.test.ts2.1 KB
  • src/__tests__/model-picker.test.ts4.3 KB
  • src/__tests__/model-route.test.ts4.4 KB
  • src/__tests__/network-policy.test.ts8.5 KB
  • src/__tests__/output-cap.test.ts2.5 KB
  • src/__tests__/pr-comment.test.ts4.5 KB
  • src/__tests__/preflight.test.ts17.7 KB
  • src/__tests__/resolve-agent-type.test.ts1.3 KB
  • src/__tests__/resolve-project-id.test.ts1.6 KB
  • src/__tests__/sandbox-tools.test.ts421 B
  • src/__tests__/setup-coordinator.test.ts16.6 KB
  • src/__tests__/setup-coverage.test.ts10.4 KB
  • src/__tests__/setup-fingerprint.test.ts1.8 KB
  • src/__tests__/setup-generated-matchers.test.ts1.2 KB
  • src/__tests__/setup-install.test.ts945 B
  • src/__tests__/setup-interaction.test.ts790 B
  • src/__tests__/setup-lock.test.ts1013 B
  • src/__tests__/setup-options.test.ts2.0 KB
  • src/__tests__/setup-output.test.ts1.3 KB
  • src/__tests__/setup-persisted-route.test.ts3.8 KB
  • src/__tests__/setup-plan.test.ts1.7 KB
  • src/__tests__/setup-project-name.test.ts624 B
  • src/__tests__/setup-protocol.test.ts1.8 KB
  • src/__tests__/setup-reporter.test.ts5.3 KB
  • src/__tests__/setup-repository-analysis.test.ts2.4 KB
  • src/__tests__/setup-state.test.ts1.4 KB
  • src/__tests__/setup-tui.test.ts2.8 KB
  • src/__tests__/setup-workspace-config.test.ts1.4 KB
  • src/__tests__/tarball.test.ts12.1 KB
  • src/__tests__/vercel-link.test.ts10.0 KB
  • src/agent-config.ts3.3 KB
  • src/agent-defaults.ts648 B
  • src/atomic-file.ts1.0 KB
  • src/auth/ensure-connected-workspace.ts6.4 KB
  • src/auth/model-picker.ts10.6 KB
  • src/auth/model-route-prompt.ts1.7 KB
  • src/auth/model-route.ts9.5 KB
  • src/auth/vercel-link.ts17.5 KB
  • src/cli.ts25.5 KB
  • src/commands/enrich.ts1.5 KB
  • src/commands/export.ts19.3 KB
  • src/commands/init-project.ts11.0 KB
  • src/commands/init.ts23.8 KB
  • src/commands/metrics.ts16.7 KB
  • src/commands/process.ts13.5 KB
  • src/commands/report.ts7.4 KB
  • src/commands/revalidate.ts5.8 KB
  • src/commands/sandbox-all.ts9.8 KB
  • src/commands/sandbox-process.ts7.7 KB
  • src/commands/scan.ts12.8 KB
  • src/commands/setup.ts5.7 KB
  • src/commands/status.ts4.8 KB
  • src/commands/triage.ts1.9 KB
  • src/config.ts1.3 KB
  • src/data-commit.ts5.8 KB
  • src/env-file.ts2.3 KB
  • src/file-sources.ts5.0 KB
  • src/formatters.ts1.1 KB
  • src/load-config.ts2.7 KB
  • src/output-cap.ts2.6 KB
  • src/pr-comment.ts4.5 KB
  • src/preflight.ts15.2 KB
  • src/quota-message.ts5.6 KB
  • src/require-dir.ts836 B
  • src/resolve-agent-type.ts467 B
  • src/resolve-project-id.ts4.6 KB
  • src/sandbox/download.ts13.5 KB
  • src/sandbox/merge-records.ts11.2 KB
  • src/sandbox/orchestrator.ts29.3 KB
  • src/sandbox/partitioner.ts5.8 KB
  • src/sandbox/request-proxy.mjs3.8 KB
  • src/sandbox/setup.ts37.2 KB
  • src/sandbox/shutdown.ts1.6 KB
  • src/sandbox/state.ts2.1 KB
  • src/sandbox/types.ts3.0 KB
  • src/sandbox/upload.ts11.7 KB
  • src/setup/coordinator.ts32.9 KB
  • src/setup/coverage.ts19.6 KB
  • src/setup/fingerprint.ts2.1 KB
  • src/setup/generated-matchers.ts4.4 KB
  • src/setup/install.ts5.7 KB
  • src/setup/interaction.ts415 B
  • src/setup/lock.ts1.8 KB
  • src/setup/options.ts1.8 KB
  • src/setup/output.ts1.9 KB
  • src/setup/persisted-route.ts1.7 KB
  • src/setup/plan.ts5.9 KB
  • src/setup/project-name.ts534 B
  • src/setup/protocol.ts5.3 KB
  • src/setup/reporter.ts14.6 KB
  • src/setup/repository-analysis.ts8.2 KB
  • src/setup/state.ts4.8 KB
  • src/setup/status.ts2.7 KB
  • src/setup/tui.tsx10.4 KB
  • src/setup/workspace-config.ts4.1 KB
  • src/version.ts2.6 KB
  • tsconfig.dts.json532 B
  • tsconfig.json159 B
  • vitest.config.ts158 B

SKILL.md (original)

Review the instructions the agent will receive before you install.

deepsec

deepsec is an AI-powered vulnerability scanner. The one-shot initializer installs this skill at .deepsec/node_modules/deepsec/SKILL.md. From inside the isolated workspace the same path is node_modules/deepsec/SKILL.md. In a Deepsec source clone, use the repository's docs/ directory instead.

When the user asks how to use, configure, or extend deepsec, read the relevant doc before answering — the docs are the source of truth, not your training data.

Where the docs are

From the target repository, .deepsec/node_modules/deepsec/dist/docs/; from inside .deepsec, node_modules/deepsec/dist/docs/; or from a Deepsec source clone, <deepsec-clone>/docs/:

  • getting-started.md — one-shot initialization and resume walkthrough
  • configuration.md — full deepsec.config.ts reference
  • plugins.md — plugin slots (matchers, notifiers, ownership, people, executor)
  • writing-matchers.md — generated declarative vs hand-authored matchers
  • models.md — model selection, defaults, refusals, future models
  • vercel-setup.md — exact project link, Sandbox scope, Gateway/BYOK/custom routes
  • architecture.md — pipeline internals
  • data-layout.md — data/ schemas (FileRecord, RunMeta, …)
  • faq.md — cost, model choice, sandbox mode, FP rate

How to answer common questions

  • "How do I install/init deepsec?" → getting-started.md; default to npx deepsec init, not a manual install/scan recipe.
  • "Setup stopped; how do I resume?" → getting-started.md + data-layout.md; re-run init or deepsec setup.
  • "How do I run another scan?" → getting-started.md after noting the first scan/process already ran during setup.
  • "What goes in deepsec.config.ts?" → configuration.md + samples/webapp/deepsec.config.ts.
  • "Why did setup generate a matcher?" → writing-matchers.md + the project's generated-matchers.ts.
  • "How do I add a richer matcher?" → writing-matchers.md + samples/webapp/matchers/*.ts.
  • "How do I write a plugin?" → plugins.md + samples/webapp/deepsec.config.ts (inline plugin pattern).
  • "What does deepsec actually do?" → architecture.md.
  • "What's in data/<id>/files/foo.json?" → data-layout.md.
  • "Which model / agent should I use?" → models.md.
  • "How do project linking, Sandbox, or my own credentials work?" → vercel-setup.md.

Read the doc before paraphrasing. The CLI flag set, defaults, and plugin-contract field names change — quote the doc, don't recall.

Agent-native initialization

When you are asked to initialize Deepsec from a non-TTY agent session, first inspect the read-only plan:

npx deepsec init --plan --output json

Then run the requested policy, normally:

npx deepsec init --yes --model-profile value --output jsonl

Parse every output line as JSON. On needs_input, show the supplied message and actions to the user rather than inventing remediation. In particular, VERCEL_AUTH_REQUIRED normally asks the user to run npx vercel login; after they do, follow the returned link action from inside .deepsec. Use npx vercel link when the user needs to choose, or the returned parameterized --yes --team <team-slug> --project <project-name> form for a known existing project. Then rerun the same Deepsec command. Exit code 2 means input is needed and exit code 3 means a requested cost/duration boundary stopped the resumable run. Never expose credential values, bypass --yes, or launch an interactive login yourself.

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

deepsec

FreeSummary

Run an AI vulnerability scan on uncommitted changes, changes against main, or an entire codebase. Filter candidate files, investigate potential security issues, and review findings with severity ratings, with options to revalidate and export results.

  • Checking uncommitted changes for vulnerabilities
  • Reviewing security issues in changes against main
  • Scanning an existing codebase
vercel-labs/deepsec8.2KUpdated Sep 29, 2026

technical-writer

FreeSummary

Write, review, and edit developer documentation for SDKs, libraries, and frameworks. Organize guides, API references, and code examples around readers’ tasks, checking technical claims against source code and official documentation while following the destination site’s conventions.

  • Writing a getting-started guide
  • Reviewing API documentation and code examples
  • Updating migration and troubleshooting guides
vercel-labs/deepsec8.2KUpdated Sep 29, 2026

See all skills by vercel-labs

Report a problem with this skill