atxp-2@0.1.0

CAUTION· static only

Publisher claims: "Agent wallet, identity, and paid tools in one package. Register an agent, fund it via Stripe or USDC, then use the balance for web search, AI image generatio..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher r-m-naveen · publishing for 272 daysInstalls 2,595Last detonated 13 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-18 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Fake instruction boundary tag; Fake instruction boundary tag; Fake instruction boundary tag. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

CRITICAL
Fake instruction boundary tagSKILL.md:228 · Fake instruction boundary tag| `npx atxp@latest image <prompt>` | Paid | AI image generation |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:230 · Fake instruction boundary tag| `npx atxp@latest video <prompt>` | Paid | AI video generation |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageSKILL.md:20 · npx invocation of non-well-known package — may execute untrusted codecreated_by: npx atxp@latest login | npx atxp@latest agent registerFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageSKILL.md:15 · npx invocation of non-well-known package — may execute untrusted codedescription: Authentication token for the ATXP API. Created by `npx atxp@latest login` or `npx atxp@latest agent register` and stored in ~/.atxp/config. Treat as a sensitive secret.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
CRITICAL
Fake instruction boundary tagSKILL.md:229 · Fake instruction boundary tag| `npx atxp@latest music <prompt>` | Paid | AI music generation |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packageSKILL.md:38 · npx invocation of non-well-known package — may execute untrusted code| `npx atxp@latest search <query>` | Web pages — may contain adversarial text |Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)SKILL.md:269 · MCP server using network transport (SSE/HTTP) — data sent over networkmcpServer: 'https://search.mcp.atxp.ai',Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04

Cost to the agent

Instructions loaded
≈3,452 tok
1 file · 2 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.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim r-m-naveen: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  3. MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim r-m-naveenPropose a patch to the maintainer