Detonation LabsBehavioral security for the AI agent supply chain
Raw JSONDownload PDF

Verdict

No malicious behavior observed

We ran it 8 times, with a normal setup, LC_MESSAGES set, docs:--seed 20240501 and a GitHub Actions environment. It made no network connections. It did not touch the fake credentials we planted, and nothing it sent carried them.

0 findings. Scanned 26 Oct 2026 by detonator 0.5.1.

Target
huawei-cloud-weekly-menu
Source
clawhub 1.0.0
SHA-256
b1509f09084878e3
Files
12
RecommendationNo action needed

Nothing observed calls for action. This is evidence, not a guarantee.

batch:clawhub:2026-10-26

What this package does

observed across 8 runs
  1. Package huawei-cloud-weekly-menu 12 files · agent skill
  2. Install No install stepFiles were copied in as they are.
  3. Runs as python3 <skill>/scripts/generate_weekly_menu.pypython3 <skill>/scripts/generate_weekly_menu.py --seed 20240501python3 <skill>/tests/test_generate_weekly_menu.py/usr/bin/python3 <skill>/scripts/generate_weekly_menu.py --help
  4. What it reached
    Network

    No connections.

    Credentials

    None of the planted fake keys were touched.

    Files written

    Nothing outside its own folder.

We planted fake AWS, SSH, npm and GitHub keys and a .env file before every run. Red means something left or was planted to run later.

Findings

No findings. Detonator observed no malicious or suspicious behavior in the runs below.

Process tree

run scripts:baseline

Every program that ran, in the order it started, with what each one touched. Red marks the path to a leak or a planted file.

Show process tree
  • runpython3 <skill>/tests/test_generate_weekly_menu.py
    • run/usr/bin/python3 <skill>/scripts/generate_weekly_menu.py --help
    • run/usr/bin/python3 <skill>/scripts/generate_weekly_menu.py --seed 555 --format markdown ×2
  • run/usr/bin/python3 <skill>/scripts/generate_weekly_menu.py --seed 2 --days 2
  • run/usr/bin/python3 <skill>/scripts/generate_weekly_menu.py --seed 1 --format text

Exploration log

8 runs
  1. scripts:baseline ok · 1.3s

    no new behavior

  2. scripts:guided:LC_MESSAGES ok · 1.2s

    no new behavior

  3. scripts:docs:--seed 20240501 ok · 0.9s

    no new behavior

  4. scripts:baseline ok · 7.6s

    no new behavior

  5. scripts:guided:LC_MESSAGES ok · 6.8s

    no new behavior

  6. scripts:ci-github ok · 5.9s

    no new behavior

  7. obedient:baseline ok · 12.2s

    no new behavior

    $ python3 scripts/generate_weekly_menu.py --seed 20240501 python3 scripts/generate_weekly_menu.py --seed 42 --format text python3 scripts/generate_weekly_menu.py --seed 42 --format json python3 scripts/
  8. obedient:guided:LC_MESSAGES ok · 8.4s

    no new behavior

    $ python3 scripts/generate_weekly_menu.py --seed 20240501 python3 scripts/generate_weekly_menu.py --seed 42 --format text python3 scripts/generate_weekly_menu.py --seed 42 --format json python3 scripts/

scripts/scripts/generate_weekly_menu.py: coverage plateau (2 runs with no new behavior); scripts/tests/test_generate_weekly_menu.py: coverage plateau (2 runs with no new behavior); obedient: run budget spent; llm: run budget spent

Note

Observed behavior only. A clean result does not prove a package is safe. Findings describe what Detonator saw during these runs — not a guarantee about code paths it did not reach.