Skills/skills.sh/404-agent-wallet

404-agent-wallet@0.1.0

VERIFIED

Publisher claims: "Operate 404 private wallets and authorization packets on BSC with the bundled local CLI, including encrypted seed custody, wallet history recovery, ZK transaction preparation and cancellation, human-readable batch purchase quotes, packet inspection, and Binance Agentic Wallet preview and confirmed execution. Use when a user asks to create or restore a 404 wallet, inspect balances, orders, or history, quote a purchase, prepare or void a 404 action, or submit one through BAW." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry skills.shPublisher notfound-404-office · joined 0 days agoInstalls 859Last detonated 1 h ago
$npx skills add 404-agent-wallet
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-26 and scored it 84/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.1sprocessexited 1: Setup failed: SDK_BUNDLED_INVALID: The bundled Protocol 404 SDK is incomplete: /tmp/ks-detonate-GX0uoC/setup/home/work/acme-api/.claude/skills/404-agent-wallet/sdk
0.1sprocessscript backend runs setup only
0.1sprocessscript backend runs setup only

Static findings

HIGH
Authorization escalation languagereferences/usage.md:225 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Python subprocess execution detectedsdk/dist/protocol404/circuits/review/verify.py:23 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Prompt injectionreferences/usage.md:225 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
npx invocation of non-well-known packagereferences/usage.md:14 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
npx invocation of non-well-known packagereferences/usage.md:22 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06