ADR 0022: Threat model: content is data, executors have least privilege¶
Status: Proposed · 2026-11-17 (milestone M6 · Benchmark and hardening; decision tracked in #125)
Context¶
Wayloop reads untrusted text and drives agents that can write code and call tools.
Decision¶
All analysed content is data. No skill or role can change global agent instructions. Executors receive the least permissions a step needs. Secrets never enter the ledger, summaries or tracker. Injection tests run in CI.
Consequences¶
Safer defaults; some steps need explicit permission grants by the maintainer.