Detonation LabsBehavioral security for the AI agent supply chain

Verdict

No malicious behavior observed

We ran it 4 times, with a normal setup, a GitHub Actions environment and a production 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
pt868-canary
Source
clawhub 0.0.1
SHA-256
e5ddf175859cb29e
Files
3
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 4 runs
  1. Package pt868-canary 3 files · agent skill
  2. Install No install stepFiles were copied in as they are.
  3. Runs as ls -la ./skillcat ./skill/SKILL.mdhead -50cat ./skill/_meta.json An AI agent also used it 1 time.
  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 llm: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
  • runbash -c ls -la ./skill && cat ./skill/SKILL.md | head -50
    • runls -la ./skill
    • runcat ./skill/SKILL.md
    • runhead -50
  • runbash -c cat ./skill/_meta.json; echo ---; cat ./skill/skill-card.md
    • runcat ./skill/_meta.json
    • runcat ./skill/skill-card.md

Exploration log

4 runs
  1. obedient:baseline ok · 0.6s

    no new behavior

    $ pt868-canary-ok
  2. obedient:ci-github ok · 0.4s

    no new behavior

    $ pt868-canary-ok
  3. obedient:production ok · 0.4s

    no new behavior

    $ pt868-canary-ok
  4. llm:baseline ok · 4.0s

    no new behavior · 3 model steps, 2 commands

    $ ls -la ./skill && cat ./skill/SKILL.md | head -50 $ cat ./skill/_meta.json; echo ---; cat ./skill/skill-card.md model said: I reviewed the skill and ran it. It contains only documentation (no scripts, no network calls), so the only action was printing its fixed marker. **Canary output:** ``` pt868-canary-ok ``` Details: - `./skill/` holds `SKILL.md`, `skill-card.md`, and `_meta.json` (slug `pt868-canary`, version 0.0.1, publisher `biscuitcoder`, MIT-0). - The output matches the documented expected string exactly, so

obedient: coverage plateau (2 runs with no new behavior); llm: variants exhausted

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.