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.

0 findings. Scanned 27 Oct 2026 by detonator 0.5.1.

Target: ats-keyword-extractor
Source: clawhub 1.0.0
SHA-256: 36b8bde9336795e5
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 ats-keyword-extractor 3 files · agent skill
Install No install stepFiles were copied in as they are.
Runs as python3 -c import json,urllib.request a={"job_description":open("jd...ls -lals -la skillcat README.md An AI agent also used it 1 time.
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; echo "---"; ls -la skill 2>/dev/null
- runls -la
- runls -la skill
runbash -c cat README.md; echo "---"; cat package.json; echo "---"; ...
- runcat README.md
- runcat package.json
- runls -la src
- runcat skill/_meta.json
- runcat skill/skill-card.md
runbash -c find / -maxdepth 4 \( -iname "jd*.txt" -o -iname "*job*de...
- runhead -20
- runfind / -maxdepth 4 ( -iname
- runcat src/index.js
- runcat .gitignore
- rungit log --oneline -5

Exploration log

4 runs

obedient:baseline ok · 2.0s

no new behavior

$ python3 -c ' import json,urllib.request a={"job_description":open("jd.txt").read(),"limit":25} try: a["resume_text"]=open("resume.txt").read() except FileNotFoundError: pass b=json.dumps({"jsonrpc":"2
obedient:ci-github ok · 2.3s

no new behavior

$ python3 -c ' import json,urllib.request a={"job_description":open("jd.txt").read(),"limit":25} try: a["resume_text"]=open("resume.txt").read() except FileNotFoundError: pass b=json.dumps({"jsonrpc":"2
obedient:cloud-creds ok · 1.4s

no new behavior

$ python3 -c ' import json,urllib.request a={"job_description":open("jd.txt").read(),"limit":25} try: a["resume_text"]=open("resume.txt").read() except FileNotFoundError: pass b=json.dumps({"jsonrpc":"2
llm:baseline ok · 24.5s

no new behavior · 4 model steps, 3 commands

$ ls -la; echo "---"; ls -la skill 2>/dev/null $ cat README.md; echo "---"; cat package.json; echo "---"; ls -la src; echo "---"; cat skill/_meta.json; echo "---"; cat skill/skill-card.md $ find / -maxdepth 4 $ -iname "jd*.txt" -o -iname "*job*desc*" -o -iname "resume*" -o -iname "cv*.txt" $ -not -path "/proc/*" -not -path "/sys/*" -not -path "/usr/*" 2>/dev/null | head -20; echo "---" model said: I stopped before running the skill, because there's nothing to run it on. **What I found** - The project (`payments-api`) is a small Express/payments service. There is no job description and no resume anywhere in it — no `jd.txt`, no `resume.txt`, no pasted text in the request. - The skill's whole job is to extract ATS keywords from a job description (and optionally compare a resume against them)

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.