dual-brain-plan

Fail

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: HIGHCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands (test and build) derived directly from project files like package.json, AGENTS.md, and CLAUDE.md. If an attacker can influence these files (e.g., in a malicious repository or pull request), they can achieve arbitrary code execution on the user's system.
  • [REMOTE_CODE_EXECUTION]: The implementation notes in executor-routing.md explicitly recommend using the --dangerously-bypass-approvals-and-sandbox flag for Codex sessions to achieve full autonomy. This removes critical security guardrails and allows the agent to perform potentially destructive actions without user oversight.
  • [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection. It ingests untrusted data from brainstorms and plans, then inlines this content directly into prompts for secondary agent sessions (sessions_spawn).
  • Ingestion points: Data enters through user-provided brainstorms and the contents of files in docs/plans/.
  • Boundary markers: The skill uses basic markdown headers (e.g., ## Plan to Review) but lacks robust delimiters or explicit instructions to the sub-agents to ignore embedded commands within the processed text.
  • Capability inventory: The spawned agents have significant capabilities, including file system access and shell execution via the OpenClaw sessions_spawn tool.
  • Sanitization: No sanitization or escaping of the inlined content is performed before passing it to the next stage of the pipeline.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 29, 2026, 09:35 AM
Security Audit — agent-trust-hub — dual-brain-plan