Verdict

No malicious behavior observed

We ran it 4 times, with a normal setup, a GitHub Actions environment and a production environment. It contacted registry.npmjs.org. It did not touch the fake credentials we planted, and nothing it sent carried them.

4 findings. Scanned 27 Oct 2026 by detonator 0.5.1.

Target: clawrouter
Source: clawhub 1.0.0
SHA-256: f9deac895822580d
Files: 3

RecommendationNo action needed

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

batch:clawhub:2026-10-27

What this package does

observed across 4 runs

Package clawrouter 3 files · agent skill
Install No install stepFiles were copied in as they are.
Runs as ls -lals -la ./skillwhich openclaw clawrouter node npmnode --version An AI agent also used it 1 time.
What it reached
Network
- registry.npmjs.org 7 connections, 1.9 KB sent
Credentials
- ./.envread
~/.npmrc read by its own tool (normal)
Files written
- ./.git/index.lockwritten

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

Used a planted key with the service it belongs to (registry.npmjs.org)

Confidence: Info A planted key went to the service it belongs to, as its login (npm to its registry, an OpenAI key to api.openai.com).
Observed in: llm:baseline

Description

A planted key was sent to the service it belongs to, only as the login header of its requests: npm sending the ~/.npmrc token to registry.npmjs.org while installing, or an app calling api.openai.com with the OpenAI key from .env (also Anthropic, Gemini, OpenRouter, Groq and xAI keys, recognized by their format).

Impact

Using the key spends your account (API costs), which is worth knowing, but the key did not reach anyone new. The key anywhere else in the request (for example inside a prompt), to any other host, or used to publish to npm, is reported as exfiltration.

Evidence

~/.npmrc (npm) sent only as the login header of requests to registry.npmjs.org

Remediation

No action needed.

F02 Low

Network destinations contacted

Confidence: Info The package connected to these hosts.
Observed in: llm:baseline

Description

Network destinations the package resolved or connected to during the runs. All traffic was captured by the sandbox; nothing reached the internet.

Impact

Context only. Unexpected destinations are worth checking against what the package claims to do.

Evidence

registry.npmjs.org

Remediation

Confirm each host is expected (the package's API, its registry). Allowlist expected egress in production.

F03 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 sed)

Remediation

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

F04 Low

A tool read its own credentials (e.g. gh, aws, ssh)

Confidence: Info A tool opened its own login or config file, such as npm reading ~/.npmrc.
Observed in: llm:baseline

Description

A tool opened its own configuration or login file, such as npm reading ~/.npmrc or gh reading its hosts file.

Impact

None in itself: this is how those tools work. Listed so the report shows every credential access.

Evidence

~/.npmrc (by npm)

Remediation

No action needed.

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 package.json; echo "---README---"; cat README.md; ech...
- runsed s/=.*/=<redacted>/ .env
  - secretread ./.env

View full process tree

runbash -c pwd; ls -la; echo "---SKILL DIR---"; ls -la ./skill 2>/de...
- runls -la
- runls -la ./skill
runbash -c which openclaw clawrouter node npm 2>/dev/null; echo "---...
- runwhich openclaw clawrouter node npm
- runnode --version
- runnpm --version
  - runnode /usr/bin/npm --version
    - secretread ~/.npmrc (its own config)
runbash -c cat package.json; echo "---README---"; cat README.md; ech...
- runsed s/=.*/=<redacted>/ .env
  - secretread ./.env
- runcat package.json
- runcat README.md
- runcat .gitignore
- runls -la src
runbash -c cat skill/_meta.json; echo "---CARD---"; cat skill/skill-...
- runcat skill/_meta.json
- runcat skill/skill-card.md
runbash -c cat src/index.js; echo "---GIT LOG---"; git log --oneline...
- runcat src/index.js
- rungit log --oneline -5
- rungit status --short
  - filewrote ./.git/index.lock
runbash -c cd /tmp && timeout 60 npm view @blockrun/clawrouter versi...
- runtimeout 60 npm view @blockrun/clawrouter version
  - runnpm view @blockrun/clawrouter version dist-tags
    - runnode /usr/bin/npm view @blockrun/clawrouter version dist-tags
      - secretread ~/.npmrc (its own config)
      - netregistry.npmjs.org:443 sent 413 B
      - netregistry.npmjs.org:443 sent 433 B
- runhead -20
runbash -c cd /tmp && timeout 90 npm view @blockrun/clawrouter versi...
- runtimeout 90 npm view @blockrun/clawrouter version
  - runnpm view @blockrun/clawrouter version
    - runnode /usr/bin/npm view @blockrun/clawrouter version
      - secretread ~/.npmrc (its own config)
      - netregistry.npmjs.org:443 sent 413 B
- runtail -20
runbash -c cd /tmp && timeout 90 npm view @blockrun/clawrouter 2>&1 ...
- runtimeout 90 npm view @blockrun/clawrouter
  - runnpm view @blockrun/clawrouter
    - runnode /usr/bin/npm view @blockrun/clawrouter
      - secretread ~/.npmrc (its own config)
      - netregistry.npmjs.org:443 sent 413 B
- runhead -40
- runnpm config get registry
  - runnode /usr/bin/npm config get registry
    - secretread ~/.npmrc (its own config)
runbash -c cd /tmp && timeout 60 curl -sS -o /dev/null -w "%{http_co...
- runtimeout 60 curl -sS -o /dev/null
  - runcurl -sS -o /dev/null -w %{http_code}\n
    - netregistry.npmjs.org:443 sent 103 B
runbash -c cd /tmp && timeout 60 curl -sS https://registry.npmjs.org...
- runtimeout 60 curl -sS https://registry.npmjs.org/@blockrun%2Fclawrouter
  - runcurl -sS https://registry.npmjs.org/@blockrun%2Fclawrouter
    - netregistry.npmjs.org:443 sent 103 B
- runnode -e let d="";process.stdin.on("data",c=>d+=c).on("end",()=>{c...
runbash -c cd /tmp && timeout 60 curl -sS https://registry.npmjs.org...
- runtimeout 60 curl -sS https://registry.npmjs.org/@blockrun%2Fclawrouter
  - runcurl -sS https://registry.npmjs.org/@blockrun%2Fclawrouter
    - netregistry.npmjs.org:443 sent 103 B
    - netDNS lookups for npmjs.org 14 queries
- runhead -c 600

Exploration log

4 runs

obedient:baseline ok · 0.8s

no new behavior

$ Your app → localhost proxy (ClawRouter) → https://blockrun.ai/api (or sol.blockrun.ai/api) ↓ OpenAI / Anthropic / $ openclaw plugins install @blockrun/clawrouter $ openclaw models set blockrun/auto openclaw models set openai/gpt-4o $ [ClawRouter] google/gemini-2.5-flash (SIMPLE, rules, confidence=0.92) Cost: $0.0025 | Baseline: $0.308 | Saved: 99.2%
obedient:ci-github ok · 0.7s

no new behavior

$ Your app → localhost proxy (ClawRouter) → https://blockrun.ai/api (or sol.blockrun.ai/api) ↓ OpenAI / Anthropic / $ openclaw plugins install @blockrun/clawrouter $ openclaw models set blockrun/auto openclaw models set openai/gpt-4o $ [ClawRouter] google/gemini-2.5-flash (SIMPLE, rules, confidence=0.92) Cost: $0.0025 | Baseline: $0.308 | Saved: 99.2%
obedient:production ok · 0.8s

no new behavior

$ Your app → localhost proxy (ClawRouter) → https://blockrun.ai/api (or sol.blockrun.ai/api) ↓ OpenAI / Anthropic / $ openclaw plugins install @blockrun/clawrouter $ openclaw models set blockrun/auto openclaw models set openai/gpt-4o $ [ClawRouter] google/gemini-2.5-flash (SIMPLE, rules, confidence=0.92) Cost: $0.0025 | Baseline: $0.308 | Saved: 99.2%
llm:baseline ok · 52.0s

new behavior: dns:registry.npmjs.org, exec:curl, ownread:./.env, ownread:~/.npmrc · 8 model steps, 11 commands

$ pwd; ls -la; echo "---SKILL DIR---"; ls -la ./skill 2>/dev/null $ which openclaw clawrouter node npm 2>/dev/null; echo "---"; node --version 2>/dev/null; npm --version 2>/dev/null $ cat package.json; echo "---README---"; cat README.md; echo "---GITIGNORE---"; cat .gitignore; echo "---ENV (keys only)---"; sed 's/=.*/=<redacted>/' .env; echo "---SRC---"; ls -la src $ cat skill/_meta.json; echo "---CARD---"; cat skill/skill-card.md $ cat src/index.js; echo "---GIT LOG---"; git log --oneline -5 2>/dev/null; echo "---STATUS---"; git status --short $ cd /tmp && timeout 60 npm view @blockrun/clawrouter version dist-tags 2>&1 | head -20 $ cd /tmp && timeout 90 npm view @blockrun/clawrouter version 2>&1 | tail -20; echo "EXIT:$?" $ cd /tmp && timeout 90 npm view @blockrun/clawrouter 2>&1 | head -40; echo "EXIT:$?"; echo "--- registry ---"; npm config get registry $ cd /tmp && timeout 60 curl -sS -o /dev/null -w "%{http_code}\n" https://registry.npmjs.org/@blockrun%2Fclawrouter 2>&1; echo "curl exit:$?" $ cd /tmp && timeout 60 curl -sS https://registry.npmjs.org/@blockrun%2Fclawrouter 2>/dev/null | node -e 'let d="";process.stdin.on("data",c=>d+=c).on("end",()=>{const j=JSON.parse(d);console.log("lates model said: I'll start by inspecting the project and the skill directory to see what's actually available.

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.