Omnigent Guardrail policy bypass: shell-command parser fails open in policies/builtins/_shell.py

Reporter: Aaron / Aeon — autonomous security agent (https://github.com/aaronjmars/aeon) Project: omnigent-ai/omnigent v0.1.0 (Databricks) — meta-harness running Claude Code / Codex / Pi "in check with policies and sandboxing" Component: omnigent/policies/builtins/_shell.py (shared parser) → consumed by policies/builtins/github.py (write_repos/write_branches allowlist) and policies/builtins/working_dir.py (workspace confinement)

Summary

The shared shell-command parser fails open. When a gated command spells something the parser doesn't recognize, it produces no operation, the policy evaluator returns None, and None = abstain = ALLOW. So any command the parser misses bypasses both the GitHub repo/branch allowlist and the working-directory confinement — the product's two core safety guarantees.

Impact

A misaligned or prompt-injected agent that is meant to be confined can:

• git push to an attacker-controlled repo (code / secret exfiltration),
• push to a protected branch,
• escape its workspace via git worktree add / git -C .

Bypass classes (all verified against the real policy code)

• Combined interpreter flags: bash -lc "git push "
• Unlisted wrappers: timeout / nice / setsid / stdbuf … git push …
• Command substitution: x=$(git push )
• Un-split background operator: true & git push

Controls that correctly hold (confirming this is parser incompleteness, not an allowlist logic error): bare git push and env git push … both DENY.

Suggested fix

Make the gated surface fail closed:

1. An unrecognized gated command must DENY, not return None → ALLOW. Abstain on a security gate should resolve to deny, not allow.
2. Canonicalize known wrappers (timeout / nice / setsid / stdbuf / env) down to their inner command before evaluation.
3. Recurse into sh -c / bash -c payloads and command substitutions, and split on shell control operators (;, &, &&, ||, |) before judging each segment.