fix(module-25): close command-injection + lab-integrity issues

- agent-job.yml: pass untrusted issue body via env (BODY), never interpolated
  into a run: shell line (fixes GHA expression-injection). Adds security note.
- lab/.gitignore: keep propose_pr's `git add -A` from sweeping __pycache__ and
  copied scaffolding into the review diff.
- agent_runner.py: simulated reject() now removes the agent's untracked files
  (git restore can't), and the Module 2 restore line only prints for the real
  tracked-edit path.
- README: clarify --simulate uses a deterministic stand-in, not the delete issue.

Closes #24
Closes #25
Closes #26
Closes #27

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01TfzV5QvtPDz8LJS3Pu5VLT
This commit is contained in:
2026-06-22 14:37:09 -04:00
parent 2684095e2f
commit c372e8452d
4 changed files with 65 additions and 9 deletions
@@ -146,6 +146,13 @@ def simulate_fix(variant: str, attempt: int) -> None:
DEMO_SRC.write_text("def discount(price, pct):\n return price - price * pct / 100\n")
def simulate_cleanup() -> None:
"""Discard the simulator's demo artifacts. These are UNTRACKED new files, so `git restore`
(which only touches tracked files) can't remove them — the simulator cleans up after itself."""
for path in (DEMO_SRC, DEMO_TEST):
path.unlink(missing_ok=True)
# --------------------------------------------------------------------------------------------------
# The endpoint every path shares: a PR PROPOSAL. Never a merge.
# --------------------------------------------------------------------------------------------------
@@ -173,12 +180,20 @@ def propose_pr(message: str) -> None:
print("\nThe agent stops here. It cannot merge. That is the whole safety model.")
def reject(reason: str, gate_output: str) -> None:
def reject(reason: str, gate_output: str, *, simulated: bool = False) -> None:
print(gate_output)
print("\n" + "=" * 80)
print(f"GATE FAILED: {reason}")
print("No PR proposed. The branch is left as-is for you to inspect or discard:")
print(" git restore . # throw the agent's change away (Module 2)")
print("No PR proposed.")
if simulated:
# The simulated agent's change is the UNTRACKED demo files, which `git restore` can't touch.
# Discard them directly so the failed attempt leaves a clean tree.
simulate_cleanup()
print("Discarded the simulated agent's demo files (agent_demo.py, test_agent_demo.py).")
print("(With a real agent editing tracked files, you'd discard with: git restore . # Module 2)")
else:
print("The branch is left as-is for you to inspect or discard:")
print(" git restore . # throw the agent's change away (Module 2)")
print("=" * 80)
@@ -198,7 +213,7 @@ def cmd_issue_to_pr(issue_path: Path, simulate: str | None) -> int:
print(gate_output)
propose_pr(f"Agent: implement {issue_path.stem}")
return 0
reject("the agent's change does not pass the gate", gate_output)
reject("the agent's change does not pass the gate", gate_output, simulated=bool(simulate))
return 1