AssemblyAI Security and Data Governance
Overview
Govern speech and derived data across every AssemblyAI surface. Keep consent, credentials, region, training posture, retention, and deletion as explicit decisions.
Prerequisites
- The target repository or integration path and the requested operator outcome.
- The AssemblyAI project, environment, region, data classification, and accountable owner.
- Current first-party documentation plus credentials only for a narrowly approved live check.
Current Contract
Speech, transcripts, prompts, and derived intelligence are governed data. Long-lived keys stay server-side; US and EU hosts are explicit decisions. Retention, training posture, transcript deletion, and downstream copies require policy evidence. Infrastructure TTL processing means physical deletion should not be described as instantaneous without confirmation.
Authentication
For live work, inject ASSEMBLYAI_API_KEY from an approved secret manager and send the raw value only in the AssemblyAI Authorization header to the configured first-party host. Never print, commit, place in a URL, or expose it to an untrusted client. Callback secrets and temporary streaming tokens are separate credentials.
Instructions
- Classify every source and derived data field.
- Confirm consent, purpose, region, training posture, and subprocessors.
- Separate, store, rotate, and monitor environment keys.
- Use temporary browser tokens and a separate callback secret.
- Minimize requested features, persisted fields, and broad access.
- Delete and reconcile AssemblyAI plus every downstream copy.
Tool Discipline
Use Read, Glob, and Grep to inspect repository code, configuration, fixtures, and evidence. Use Write and Edit only for approved implementation or documentation changes. Do not call AssemblyAI, upload audio, open a streaming session, mint a token, replay a callback, deploy, rotate a key, or delete a transcript merely because this skill was invoked.
Approval Boundaries
Require an accountable owner before live audio processing, production credential or endpoint changes, paid model or capacity changes, content retention, callback replay, deployment, or deletion. Read-only repository inspection and synthetic offline validation do not authorize live vendor actions.
Failure Modes
- Deleting the vendor transcript does not remove downstream copies.
- PII redaction does not replace consent or authorization.
- A client-side project key is compromised even in a private repository.
Output
Return the operation scope, environment, region, contract surface, authorization class, model and feature decisions, deterministic validation results, content-free identifiers, risks, cleanup or rollback state, and a concise pass/fail receipt. Exclude credentials, signed URLs, audio, transcript text, prompts, and customer-derived content.
Example
- Start with the named environment, approved regional host, synthetic fixture identity, and bounded operation budget.
- Finish with safe IDs, contract and assertion counts, terminal state, cleanup status, and the decision owner; never reproduce speech content.
Validation
Rerun the smallest relevant deterministic check, compare actual state with the requested outcome and current first-party contract, verify sensitive fields are absent from evidence, and confirm rollback, termination, or deletion state before reporting success.
References
Review the dated first-party evidence map before relying on any model, parameter, limit, price, region, or lifecycle claim.