AI Agent OPSEC — Runtime Classified Data Enforcer
Prevent your AI agent from leaking classified terms to external APIs, subagents, or logs. Term registry + runtime redaction + pre-publish audit. Zero dependencies, zero network calls.
AI Agent OPSEC — Runtime Classified Data Enforcer
Keep your secrets out of web searches, external LLM calls, and subagent spawns.
Side Effects (Declared)
| Type | Path | Description |
|---|---|---|
| READS | <workspace>/classified/classified-terms.md | Your term registry — add terms here once, protected everywhere |
| WRITES | <workspace>/memory/security/classified-access-audit.jsonl | Append-only audit log; auto-rotates at 1MB; never contains original sensitive text |
| NETWORK | None | Zero external calls. Fully local. |
Important: Add
classified/andmemory/security/to your.gitignoreto prevent accidental commits.
Setup
- Create
classified/classified-terms.mdin your workspace root - Add one term per line (blank lines and
#comments ignored) - Require and use the enforcer before any external call
const ClassifiedAccessEnforcer = require('./src/ClassifiedAccessEnforcer');
const enforcer = new ClassifiedAccessEnforcer('/path/to/workspace');
// Before any external API call
const { safe, payload } = enforcer.gateExternalPayload(userQuery, 'web_search');
// Before spawning a subagent
const { task } = enforcer.redactTaskBeforeSpawn(taskString, 'ResearchAgent');
See README.md for full documentation.
Related skills
- Downloads
- 1.6kAll time
- Security audit
- Review
- Last updated
- 6mo ago
- Current version
- v1.4.0
- License
- MIT-0
