Skip to content

Privacy notice

Last updated: 2026-11-19.

This notice covers the agent-bom software, its directory plugins, and the public lookup service at https://agent-bom-lookup.up.railway.app (the "lookup service"), which is operated by Mohamed Wagdy Saad, operating as Koda AI ("we"). Apart from the lookup service, the agent-bom project offers no public hosted service, and the software and plugins send the project no data. Anyone else who runs agent-bom as a service for others is its operator, and that operator's own notice applies to what they store.

Status: the lookup service is not yet deployed; that address does not answer yet. Until it does, no data reaches it, and the sections about it describe how it will handle requests once it is live.

Scope and information processed

agent-bom is security scanning software that can run locally or in an operator-controlled service. These modes have different data boundaries.

Local directory plugins run selected inventory, package, configuration and skill checks. Depending on the requested tool, inputs include package names and versions, selected file paths and contents, MCP server definitions, environment variable names, vulnerability identifiers and findings. Discovery can read known client configuration locations; preview them with agent-bom where --dry-run. Directory skills and the audit profile do not expose the agent_activity tool or a skill for reading chat history. Other explicitly selected standalone features have their own permissions; installing a directory plugin does not authorize them.

The agent-bom-guard plugin adds one hook. Claude Code passes it the text of every Bash command before it runs, and it parses that text on your machine to find package installs. It stores nothing and writes no files. With its osv_lookup option on, which is the default, it sends the name, ecosystem and pinned version of each package an install names to api.osv.dev, even when the install uses a custom registry, so a private package name reaches that service unless the option is off. It sends no command text, paths, file contents, environment variables or credentials.

No directory plugin reads Claude or Codex chat history, session files or memory. ~/.claude.json is read for its MCP server entries; the prompt history it also holds is not used or returned.

A remote MCP service receives the tool name and arguments sent by the client, including any supplied paths, package names or evidence, and returns tool results to that client. Remote paths refer to the server's filesystem, not the client's computer. The client and its AI provider may retain those messages under their own policies. Do not submit secrets or personal information that the selected scan does not require. Redaction reduces exposure but is not a guarantee that arbitrary input is free of sensitive information.

Destinations

Package and vulnerability lookups can send package names, versions, advisory IDs and repository coordinates to OSV, NVD, FIRST EPSS, CISA, npm, PyPI and OpenSSF Scorecard. Installation through uvx downloads software from the configured package index. These providers also receive ordinary network request metadata. The scanner's lookup requests do not upload entire project files. Offline scanning uses available local evidence and can have coverage gaps.

Refreshing the local advisory database, which no directory skill does on its own, downloads public feeds from osv-vulnerabilities.storage.googleapis.com, secdb.alpinelinux.org, security-tracker.debian.org, deb.freexian.com, epss.empiricalsecurity.com, CISA and NVD, and sends no package or project data.

The agent-bom Claude plugin starts its servers with GITHUB_TOKEN, GH_TOKEN and NVD_API_KEY blanked. When agent-bom runs from a shell, as the Codex skills do, a GITHUB_TOKEN or GH_TOKEN already in that environment is sent only to api.github.com, and NVD_API_KEY only to services.nvd.nist.gov, to raise rate limits.

Hosted OAuth sends users to the configured authorization server for login and consent. The MCP service validates the access token's issuer, subject, tenant, audience and expiry, then sends that token to the same issuer's configured introspection endpoint to check whether it remains active. Passwords are entered at the authorization server; the MCP service does not implement a password-login form. Authentication, hosting and identity-provider logs are subject to those operators' configurations.

Explicitly configured control-plane pushes, exports, cloud connectors, webhooks and telemetry collectors have separate destinations and permissions. They are not enabled by installing a directory skill. The permissions contract lists the supported destinations and opt-in behavior.

Storage and retention

  • Local report files remain until the user or an operator removes them. Local rescan summaries retain one bounded identity summary per target, up to 200 targets by default; AGENT_BOM_NO_SCAN_MEMORY=1 disables that feature.
  • The MCP scan-result store uses SQLite or configured PostgreSQL. Its default readable lifetime is 30 minutes, configurable by AGENT_BOM_MCP_SCAN_RESULT_TTL_SECONDS, with four results per tenant by default. Expired rows are removed when a subsequent result is stored; expiration is not a guaranteed deletion deadline for database files, backups or replicas. Cached results are bound to a tenant and caller token; token rotation prevents access to the preceding token's cached results.
  • Recent MCP request traces are held in process memory, bounded to 256 entries by default. Operational logs, persisted inventory, audit records and backups have operator-controlled retention. This code does not impose one universal deletion period on every deployment or external provider.
  • The resource server caches public verification keys for five minutes. It checks token activity on each HTTP authentication request without caching a successful introspection decision. Client-side refresh-token storage belongs to the MCP client and authorization server.

The operator of a hosted or self-hosted deployment sets its log, backup and identity-account retention, and must document those settings and its deletion process.

Public lookup service

The lookup service answers two read-only questions over MCP, with no account or sign-in: whether a package version has known vulnerabilities (check), and what an advisory id refers to (intel_lookup).

  • What you send. Only the tool arguments: a package name, ecosystem and optional version, or one advisory id. Do not put personal information in them. The service reads no file or setting you choose.
  • Where it goes. check sends the package coordinate to api.osv.dev and api.github.com (public security advisories). When you give no version, it asks the package's registry for the latest release: registry.npmjs.org, pypi.org, proxy.golang.org, crates.io or search.maven.org. For npm and PyPI packages it can also confirm with registry.npmjs.org or pypi.org that the version is published. intel_lookup reads the service's own advisory database and contacts nothing. At start-up the service downloads public advisory data from osv-vulnerabilities.storage.googleapis.com, CISA and epss.empiricalsecurity.com, sending nothing about you. These providers receive ordinary network request metadata from the service, not your address.
  • What we keep. In memory, the last 256 calls (tool name, your network address as the rate-limit key, status and duration, and for a call that fails its error message, which can repeat the package name you sent; not the arguments themselves) and per-address rate-limit counters. On the service's disk, a cache of advisory answers keyed by package coordinate, with no caller identity, reused for up to 24 hours. The service has no persistent storage: the cache is lost whenever the service is redeployed, and the in-memory records whenever it restarts.
  • Hosting. The service runs on Railway. Railway's request logs record your network address, the request method, path and status. The service's own log, which Railway also keeps, records each call's tool name, your network address and duration, and for a call that fails its error message, which can repeat the package name you sent. Both are kept under Railway's own retention and privacy policy.
  • No accounts, cookies, tracking, advertising, profiling or sale of data. The service is not directed at children.
  • Your requests. We hold no account or profile for you and cannot link a call to a person. For questions or requests about the lookup service, contact wagdy@koda-studio.dev.

Purposes and your controls

The information above is processed only to produce the security result you asked for. There is no telemetry, advertising or profiling in the plugins. You can preview what is read with agent-bom where --dry-run, turn off network lookups with offline mode or the guard's osv_lookup option, turn off rescan summaries with AGENT_BOM_NO_SCAN_MEMORY=1, and delete local data by removing ~/.agent-bom.

Access and questions

Apart from the lookup service described above, the project holds no records about you from these tools. For data stored by a hosted or self-hosted deployment, contact its operator. Use the project's support channel for general questions without including private records. Report security concerns through the private reporting instructions. No certification or regulatory compliance status is asserted by this notice.