cli@4.10.1
CAUTIONPublisher claims: "Official command line interface for the Box API. Includes official AI agent skills: box/box-for-ai." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-26 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Process kill command; npx invocation of non-well-known package; Prompting user to enter sensitive credentials. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationst+CategoryObserved action
0.1sprocessexited 1: Node.js v22.23.4
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
Static findings
HIGH
Process kill commandsrc/box-command.js:385 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05HIGH
npx invocation of non-well-known packageREADME.md:18 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06CRITICAL
Prompting user to enter sensitive credentialsREADME.md:82 · Prompting user to enter sensitive credentials — social engineeringFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03HIGH
Auto-update or dynamic fetch configurationsrc/github-updater.js:126 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06HIGH
Auto-update or dynamic fetch configurationsrc/github-updater.js:72 · Auto-update or dynamic fetch configuration — agent may load new code at runtimeFix: Pin versions and sources; vendor anything fetched at install time.
AST06MEDIUM
File type combined with upload actionsrc/box-command.js:1308 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07HIGH
npx invocation of non-well-known packagepackage.json:97 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06CRITICAL
HTML comment carrying imperative instructions to the agentREADME.md:22 · HTML comment carrying imperative instructions to the agentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01What would make this Verified
17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim box: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- Process kill command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- npx invocation of non-well-known package≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
- Auto-update or dynamic fetch configuration≈ +4 on the totalPin versions and sources; vendor anything fetched at install time.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim box