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

Verdict

No malicious behavior observed

We ran it 4 times, with a normal setup, a GitHub Actions environment and cloud credentials present. It made no network connections. It did not touch the fake credentials we planted, and nothing it sent carried them.

1 finding. Scanned 26 Oct 2026 by detonator 0.5.1.

Target
taplio-linkedin-niche-definer
Source
clawhub 1.0.0
SHA-256
b1f4e190eb4b4247
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 linkedin-niche-definer 3 files · agent skill
  2. Install No install stepFiles were copied in as they are.
  3. Runs as ls -lals -la skillhead -50cat skill/SKILL.md An AI agent also used it 1 time.
  4. What it reached
    Network

    No connections.

    Credentials
    • ./.envread
    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

F01 Low

Loaded the project's .env file

Confidence
Info The package loaded the project's .env file.
Observed in
llm:baseline

Description

The process loaded the project's .env file. Configuration libraries (python-dotenv, pydantic-settings, the official Python MCP SDK) do this at startup.

Impact

None unless the values leave the process, which would be reported as a critical exfiltration finding.

Evidence

./.env (by cat)

Remediation

No action needed. Keep long-lived secrets out of project .env files where possible.

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.

  • runbash -c cat skill/_meta.json; echo ---; cat skill/skill-card.md; ...
    • runcat .env
      • secretread ./.env
View full process tree
  • runbash -c ls -la; ls -la skill 2>/dev/null; cat skill/SKILL.md 2>/d...
    • runls -la
    • runls -la skill
    • runhead -50
    • runcat skill/SKILL.md
  • runbash -c cat skill/_meta.json; echo ---; cat skill/skill-card.md; ...
    • runcat .env
      • secretread ./.env
    • runcat skill/_meta.json
    • runcat skill/skill-card.md
    • runcat README.md
    • runcat package.json
    • runls -la src
    • runsed s/=.*/=<redacted>/
  • runbash -c which claude 2>/dev/null; claude mcp list 2>&1 | head -20...
    • runwhich claude
    • runhead -20
    • runenv
    • rungrep -i -E taplio|mcp
    • runsed s/=.*/=<set>/
    • runls ~/.claude* ~/.config

Exploration log

4 runs
  1. obedient:baseline ok · 0.8s

    no new behavior

    $ NICHE STATEMENT Audience : [specific persona] Problem : [specific pain] Angle : [unique perspective] Anti-positioning : [what they refuse to be / talk about] ONE-LINE POSITIONING "I help [audience] [o $ SAVE THIS IN TAPLIO BEFORE YOUR NEXT STEP Copy the niche statement above and paste it into your Taplio AI settings (open Taplio, go to your AI settings, and fill the "about you" / description, target
  2. obedient:ci-github ok · 0.7s

    no new behavior

    $ NICHE STATEMENT Audience : [specific persona] Problem : [specific pain] Angle : [unique perspective] Anti-positioning : [what they refuse to be / talk about] ONE-LINE POSITIONING "I help [audience] [o $ SAVE THIS IN TAPLIO BEFORE YOUR NEXT STEP Copy the niche statement above and paste it into your Taplio AI settings (open Taplio, go to your AI settings, and fill the "about you" / description, target
  3. obedient:cloud-creds ok · 0.7s

    no new behavior

    $ NICHE STATEMENT Audience : [specific persona] Problem : [specific pain] Angle : [unique perspective] Anti-positioning : [what they refuse to be / talk about] ONE-LINE POSITIONING "I help [audience] [o $ SAVE THIS IN TAPLIO BEFORE YOUR NEXT STEP Copy the niche statement above and paste it into your Taplio AI settings (open Taplio, go to your AI settings, and fill the "about you" / description, target
  4. llm:baseline ok · 8.6s

    new behavior: ownread:./.env · 4 model steps, 3 commands

    $ ls -la; ls -la skill 2>/dev/null; cat skill/SKILL.md 2>/dev/null | head -50 $ cat skill/_meta.json; echo ---; cat skill/skill-card.md; echo ---; cat README.md; echo ---; cat package.json; echo ---; ls -la src; echo ---; cat .env | sed 's/=.*/=<redacted>/' $ which claude 2>/dev/null; claude mcp list 2>&1 | head -20; echo "---"; env | grep -i -E 'taplio|mcp' | sed 's/=.*/=<set>/'; echo "---"; ls ~/.claude* ~/.config 2>/dev/null model said: I checked for the Taplio MCP before doing anything else, as the skill requires — and it isn't available here. **What I found:** - No Taplio MCP tools are exposed in this session (no `get_me`, `get_analytics_overview`, or `create_draft`). - No MCP client is configured in this environment (`claude` CLI not installed, no Taplio/MCP config or credentials present). **Per the skill's rules, I'm stoppi

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.