Verdict

No malicious behavior observed

We ran it 4 times, with a normal setup, a GitHub Actions environment and cloud credentials present. It contacted registry.npmjs.org. It read some credential files, but nothing it sent carried them.

5 findings. Scanned 27 Oct 2026 by detonator 0.5.1.

Target: cli-memo
Source: clawhub 1.0.0
SHA-256: 5c1d5f9a02655fad
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 cli-memo 3 files · agent skill
Install No install scripts of its ownOnly the package manager ran.
Runs as head -100ls -lals skillwhich node npm npx An AI agent also used it 1 time.
What it reached
Network
- registry.npmjs.org 8 connections, 2.3 KB sent
Credentials
- ./.envread
- ~/.npmrcread
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

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 cat)

Remediation

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

F04 Low

Agent read credential files (may be the agent's own choice)

Confidence: Info A credential file was opened by a program that does not own it.
Observed in: llm:baseline

Description

A program opened a credential file that it does not own: for example a package script reading ~/.npmrc, ~/.aws/credentials or ~/.ssh/id_rsa, rather than npm, the AWS CLI or ssh reading their own files. The reading program is named in the evidence. In this run the contents were not seen leaving the sandbox.

Impact

Reading credentials is the collection step that precedes theft. Exfiltration may be gated on conditions this run did not meet (a different date, CI variables, a reachable network), or the data may be staged for a later step.

Evidence

~/.npmrc (by cat, npm)

Remediation

Review why this package needs the file. Legitimate tools read only their own configuration; anything else should be treated as hostile until explained. Prefer running it with credentials unavailable (separate user, container, or scoped environment).

References

ATT&CK T1552.001 Credentials in Files
CWE-200 Exposure of Sensitive Information
OWASP MCP01:2025 Token Mismanagement & Secret Exposure

F05 Low

Agent put secrets in the model's context (may be the agent's own choice)

Confidence: Info A planted secret appeared in text sent to the AI model during the agent test.
Observed in: llm:baseline

Description

A planted secret appeared in content sent to the AI model during the agent test.

Impact

The model provider saw the value; it did not leave through the package.

Evidence

./.env (dotenv)

Remediation

Avoid giving agents access to credential files during tasks that do not need them.

References

OWASP LLM02:2025 Sensitive Information Disclosure

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 README.md .env .gitignore; ls src; cat s...
- runcat package.json README.md .env .gitignore
  - secretread ./.env
runbash -c cat ~/.npmrc 2>/dev/null; cat /usr/etc/npmrc 2>/dev/null;...
- runcat ~/.npmrc
  - secretread ~/.npmrc

View full process tree

runbash -c cd . && memo --version; memo guide --json 2>&1 | head -100
- runhead -100
runbash -c ls -la; ls skill; which node npm npx; npm ls -g --depth=0...
- runls -la
- runls skill
- runwhich node npm npx
- runnpm ls -g --depth=0
  - runnode /usr/bin/npm ls -g --depth=0
    - secretread ~/.npmrc (its own config)
    - netregistry.npmjs.org:443 sent 431 B
runbash -c cat package.json README.md .env .gitignore; ls src; cat s...
- runcat package.json README.md .env .gitignore
  - secretread ./.env
- runls src
- runcat skill/_meta.json skill/skill-card.md
runbash -c npm install -g @wirecat/cli-memo 2>&1 | tail -20; which m...
- runnpm install -g @wirecat/cli-memo
  - runnode /usr/bin/npm install -g @wirecat/cli-memo
    - secretread ~/.npmrc (its own config)
    - netregistry.npmjs.org:443 sent 410 B
- runtail -20
- runwhich memo
runbash -c npm view @wirecat/cli-memo version 2>&1 | tail -5; npm co...
- runnpm view @wirecat/cli-memo version
  - runnode /usr/bin/npm view @wirecat/cli-memo version
    - secretread ~/.npmrc (its own config)
    - netregistry.npmjs.org:443 sent 407 B
- runtail -5
- runnpm config get registry
  - runnode /usr/bin/npm config get registry
    - secretread ~/.npmrc (its own config)
- runnpm view @wirecat/cli-memo
  - runnode /usr/bin/npm view @wirecat/cli-memo
    - secretread ~/.npmrc (its own config)
    - netregistry.npmjs.org:443 sent 407 B
- runhead -20
runbash -c npm view @wirecat/cli-memo --json 2>&1 | head -40; echo "...
- runhead -40
- runnpm view @wirecat/cli-memo --json
  - runnode /usr/bin/npm view @wirecat/cli-memo --json
    - secretread ~/.npmrc (its own config)
    - netregistry.npmjs.org:443 sent 407 B
- runcurl -s -o /dev/null -w %{http_code}\n
  - netregistry.npmjs.org:443 sent 100 B
runbash -c curl -s https://registry.npmjs.org/@wirecat%2Fcli-memo | ...
- runcurl -s https://registry.npmjs.org/@wirecat%2Fcli-memo
  - netregistry.npmjs.org:443 sent 100 B
- runhead -c 600
- runcurl -s https://registry.npmjs.org/@wirecat%2Fcli-memo
  - netregistry.npmjs.org:443 sent 100 B
  - netDNS lookups for npmjs.org 16 queries
- runpython3 -c import sys,json; d=json.load(sys.stdin); print(list(d.key...
runbash -c cat ~/.npmrc 2>/dev/null; cat /usr/etc/npmrc 2>/dev/null;...
- runcat ~/.npmrc
  - secretread ~/.npmrc
- runcat /usr/etc/npmrc
- runnpm config list
  - runnode /usr/bin/npm config list
    - secretread ~/.npmrc (its own config)
- runhead -30
- runenv
- rungrep -i -E npm|registry|proxy

Exploration log

4 runs

obedient:baseline ok · 0.5s

no new behavior

$ memo search people <name> --json # who: person:<id> for --contact, across every account memo context telegram:<id or name> --json # one person: messages, mail, notes, tasks memo
obedient:ci-github ok · 0.7s

no new behavior

$ memo search people <name> --json # who: person:<id> for --contact, across every account memo context telegram:<id or name> --json # one person: messages, mail, notes, tasks memo
obedient:cloud-creds ok · 0.4s

no new behavior

$ memo search people <name> --json # who: person:<id> for --contact, across every account memo context telegram:<id or name> --json # one person: messages, mail, notes, tasks memo
llm:baseline ok · 51.9s

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

$ cd . && memo --version; memo guide --json 2>&1 | head -100 $ ls -la; ls skill; which node npm npx; npm ls -g --depth=0 2>/dev/null $ cat package.json README.md .env .gitignore; ls src; cat skill/_meta.json skill/skill-card.md $ npm install -g @wirecat/cli-memo 2>&1 | tail -20; which memo; memo --version $ npm view @wirecat/cli-memo version 2>&1 | tail -5; npm config get registry; npm view @wirecat/cli-memo 2>&1 | head -20 $ npm view @wirecat/cli-memo --json 2>&1 | head -40; echo "exit=$?"; curl -s -o /dev/null -w '%{http_code}\n' https://registry.npmjs.org/@wirecat%2Fcli-memo $ curl -s https://registry.npmjs.org/@wirecat%2Fcli-memo | head -c 600; echo; curl -s https://registry.npmjs.org/@wirecat%2Fcli-memo | python3 -c "import sys,json; d=json.load(sys.stdin); print(list(d.k $ cat ~/.npmrc 2>/dev/null; cat /usr/etc/npmrc 2>/dev/null; npm config list 2>&1 | head -30; env | grep -i -E 'npm|registry|proxy' model said: The `memo` binary isn't installed. Let me install it per the skill's install instructions.

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.