Skills/ClawHub/basemail

basemail@1.9.0

VERIFIED· install only

Publisher claims: "📬 BaseMail - Onchain Email for AI Agents on Base. Get [email protected] linked to your Basename (.base.eth). SIWE wallet auth, no CAPTCHA, no passwords. Give your agent a verifiable email identity on Base Chain — register for services, send emails, and receive confirmations autonomously." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher daaab · publishing for 78 daysInstalls 3,540Last detonated 6d ago
$clawhub install basemail
WatchReport an issue

Coverage

Install scripts ran; no agent task scenario for this bundle.
Tested
install scripts, with decoy credentials in place · second launch with the clock 45 days ahead · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; install scripts ran; no agent task scenario for this bundle) on 2026-11-08 and scored it 84/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.1sprocessexited 1: Node.js v22.23.4
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only
0.2sprocesssecond launch, clock +45 days, CI unset
0.3sprocessexited 1: Node.js v22.23.4

Static findings

HIGH
Agent configured for autonomous execution without human approvalSKILL.md:42 · Agent configured for autonomous execution without human approval- **Autonomous for AI agents** — Register for services, submit forms, receive confirmations without human helpFix: Declare and request only the permissions the task needs.
AST02
MEDIUM
File type combined with upload actionscripts/send.js:39 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('範例: node send.js [email protected] "Hello" "How are you?"');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/send.js:38 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('用法: node send.js <收件人> <主旨> <內文>');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/register.js:291 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(' node scripts/send.js [email protected] "Hi" "Hello!"');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File permission modification commandSKILL.md:109 · File permission modification command — agent changes file ownership/permissions4. Private key files should be chmod `600` (owner read/write only)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandSKILL.md:173 · File permission modification command — agent changes file ownership/permissions├── token.json # Auth token + refresh_token + expires_at (chmod 600)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandSKILL.md:171 · File permission modification command — agent changes file ownership/permissions├── private-key.enc # Encrypted private key (AES-256-GCM, chmod 600)Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File type combined with upload actionSKILL.md:221 · File type combined with upload action — agent may exfiltrate local data files- `token.json` stores `refresh_token` + `expires_at`; `send.js` / `inbox.js` renew the token automatically (and retry once on 401) — the private key is only needed for the first registrationFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈2,344 tok
1 file · 11 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.