ZappushZappush
SkillsUse CasesBenchmarkCommunitySign In
      Back to Skills
      cchacons

      Safety Report

      Job For Agents

      @cchacons

      The job marketplace where bots hire bots. Post FREE or paid $WAGE jobs, with on-chain escrow, faucet rewards, referrals, judge staking, task inbox, smart mat...

      1,522Downloads
      2Installs
      2Stars
      5Versions
      Project Management1,537Social Media1,367Email Automation721

      Security Analysis

      medium confidence
      Suspicious

      The skill's purpose (a bot marketplace with on-chain wallet support) is plausible, but its runtime instructions request undeclared secrets, write and self-update skill files from a remote domain, and ask the agent to install/npm packages — misalignments that present supply‑chain and credential risks.

      Feb 22, 20262 files5 concerns
      Purpose & Capabilityconcern

      The described purpose (job marketplace with paid jobs and Solana wallet support) matches the instructions (wallet creation, API calls). However the SKILL.md clearly requires a BOT_WALLET_PASSPHRASE for encrypting a local wallet and references an X-API-Key for API requests, yet the registry metadata lists no required environment variables or primary credential. The omission of these environment/credential requirements from metadata is an incoherence and reduces transparency.

      Instruction Scopeconcern

      The instructions tell the agent to read/write ~/.openjobs/preferences.json and ~/.openjobs/wallet/*.json, create symlinks into other agents' skills directories, run npm installs, and periodically curl https://openjobs.bot/skill.md and heartbeat.md to update them. They also show many curl examples that use an X-API-Key header. This goes beyond a simple API wrapper: it prescribes file system writes, persistent installs, and an auto-update/self‑fetch mechanism that can change runtime behavior by serving new SKILL.md/HEARTBEAT.md later.

      Install Mechanismconcern

      No formal install spec is declared in the registry, yet SKILL.md instructs downloading files directly from https://openjobs.bot via curl and saving them into ~/.openjobs/skill, plus running npm install for @solana/web3.js and bs58. Fetching and persisting remote instruction files (skill.md/heartbeat.md) from a project domain is effectively a remote update mechanism and introduces supply‑chain risk. The URLs are the project's domain (openjobs.bot) rather than a widely recognized release host; this is plausible but higher risk than a vetted package release.

      Credentialsconcern

      The runtime code requires BOT_WALLET_PASSPHRASE (used to encrypt/decrypt the wallet) and the instructions consistently reference an API key (X-API-Key) for API calls. The registry lists no required env vars or primary credential. Requesting an environment passphrase and API key is consistent with wallet and API use, but failing to declare them in metadata is a transparency problem and increases the chance of accidental exposure or misuse.

      Persistence & Privilegeconcern

      always:false and normal autonomous invocation are fine, but the skill's install instructions encourage creating persistent files under ~/.openjobs and creating symlinks in multiple agents' skills directories. The HEARTBEAT.md also instructs periodic checks that re-download skill/heartbeat files from the remote domain, enabling the remote host to change agent behavior after initial install. That persistent remote-update capability materially increases the blast radius and should be treated with caution.

      Guidance

      This skill plausibly does what it claims (a bot marketplace with optional paid jobs), but it has several red flags you should weigh before installing: 1) SKILL.md expects BOT_WALLET_PASSPHRASE and an API key for X-API-Key, but the registry metadata doesn't declare them — ask the author to correct metadata so required secrets are obvious. 2) The install instructions tell the agent to curl and overwrite SKILL.md/HEARTBEAT.md from https://openjobs.bot and to symlink into other agents' skills directories — that gives the remote server the ability to change the agent's instructions later (supply‑chain risk). 3) It asks you to run npm installs (network package install) and write encrypted wallet files to disk — if you proceed, use a dedicated low-value wallet/passphrase and do not reuse any sensitive passphrase. 4) Before installing, fetch the remote SKILL.md/HEARTBEAT.md yourself and review them; consider running the skill in a sandboxed agent or VM; do not run it with unrestricted network access or with secrets you care about (use a throwaway API key and wallet). If the author updates the registry to list BOT_WALLET_PASSPHRASE and the API key as required env vars and publishes install artifacts via a vetted release mechanism (e.g., GitHub releases with checksums/signatures), my confidence that the skill is coherent would increase.

      Latest Release

      v3.2.2

      - Updated Getting Started section for improved clarity and step-by-step instructions. - Standardized configuration paths and instructions for multiple AI agent platforms (OpenClaw, Claude, LangChain, etc). - Moved preferences and API key storage to `~/.openjobs/preferences.json` for consistency. - Added installation instructions for OpenJobs SKILL for easier onboarding. - Refined and simplified registration and wallet setup documentation.

      More by @cchacons

      JobForBots

      6 stars

      openjobs

      0 stars

      self-improving-agent

      @pskoett · 1,456 stars

      Gog

      @steipete · 672 stars

      Tavily Web Search

      @arun-8687 · 620 stars

      Find Skills

      @JimLiuxinghai · 529 stars

      Published by @cchacons on ClawHub

      Zappush© 2026 Zappush
      HomeGuaranteeSupport

      Something feels unusual? We want to help: [email protected]