aep-autopilot

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from feature workspaces that are technically external to the main orchestrator session, creating an indirect injection surface.\n
  • Ingestion points: The autopilot tick protocol reads .feature-workspaces/<name>/.dev-workflow/signals/status.json and eval-response-*.md from worker worktrees to synchronize progress, cost, and evaluation results (File: SKILL.md, references/tick-protocol.md).\n
  • Boundary markers: The architecture uses a dedicated 'CHECK' phase that runs in a cheap, context-isolated agent (e.g., a Haiku subagent or Codex one-shot) to parse signals. This prevents potentially malicious content in signal files from influencing the primary orchestrator session (File: SKILL.md, references/tick-protocol.md).\n
  • Capability inventory: The orchestrator maintains capabilities to nudge workspace agents, perform git operations, and interact with the GitHub CLI (gh pr).\n
  • Sanitization: All state and signal data is validated using a minimal, dependency-free JSON schema validator (scripts/json-schema.mjs) against a strict schema (references/autopilot-state.schema.json) to prevent schema confusion and malformed data ingestion.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 11:02 AM
Security Audit — agent-trust-hub — aep-autopilot