ZappushZappush
SkillsUse CasesBenchmarkCommunitySign In
      Back to Skills
      aerialcombat

      Safety Report

      Agent Directory

      @aerialcombat

      The directory for AI agent services. Discover tools, platforms, and infrastructure built for agents.

      4,880Downloads
      40Installs
      10Stars
      2Versions
      File Management2,100DevOps & Infrastructure1,045Design & Prototyping842

      Security Analysis

      high confidence
      Clean0.04 risk

      This is an instruction-only directory skill that coherently points agents to a JSON listing and linked skill.md files; it requests no credentials or installs — but fetching and following third‑party skill.md files is where risk may arise.

      Feb 11, 20261 files1 concern
      Purpose & Capabilityok

      Name/description (agent directory) matches the instructions: fetch services.json and individual skill.md files. The skill requests no unrelated binaries, env vars, or config paths.

      Instruction Scopenote

      SKILL.md instructs the agent to curl ctxly.com/services.json and to fetch other services' skill.md files. That is expected for a directory, but it gives the agent broad discretion to retrieve and then act on third‑party skill.md content — downstream skill.md files could request credentials or additional actions. The directory itself does not instruct reading local files or secrets.

      Install Mechanismok

      No install spec and no code files are present; nothing will be written to disk by this skill itself.

      Credentialsok

      No environment variables, credentials, or config paths are requested. Required privileges are minimal and proportionate to the directory purpose.

      Persistence & Privilegeok

      always is false and the skill does not request persistent system changes or modify other skills' configs. Normal autonomous invocation is allowed by platform default.

      Guidance

      This skill is a simple index: it points your agent at ctxly.com/services.json and to external skill.md files. Before allowing your agent to automatically follow and execute third‑party skill.md instructions, review those linked skill.md documents manually (or restrict the agent's network access). Do not expose secrets when testing links; verify linked service domains and prefer HTTPS (the skill uses HTTPS). If you enable autonomous use, consider sandboxing network calls or limiting which services the agent may fetch/activate to avoid accidentally executing untrusted instructions.

      Latest Release

      v1.2.0

      - Updated directory to new domain: ctxly.com, with revised endpoints and workflows. - Directory description expanded to include tools, platforms, and infrastructure. - All listed services now include a direct link to their skill.md file. - Categories expanded and described for clearer navigation. - Service submission is now via email instead of API. - Updated homepage and API base URLs to ctxly.com.

      More by @aerialcombat

      Ctxly Home

      0 stars

      MyMemory.bot

      0 stars

      Ctxly Chat

      0 stars

      self-improving-agent

      @pskoett · 1,456 stars

      Gog

      @steipete · 672 stars

      Tavily Web Search

      @arun-8687 · 620 stars

      Published by @aerialcombat on ClawHub

      Zappush© 2026 Zappush
      HomeGuaranteeSupport

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