pica — security grade SAFE, quality 71/100

Security audit verdict: SAFE · quality 71/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by withoneai · Agent Tool · ★ 1.5k

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is pica safe to install? View the security audit →

About pica

Pica Community Edition - Ensuring outcomes for the AI-first world Website · Documentation · Dashboard · Changelog · X · LinkedIn Note: This repository is the Community Edition of Pica and is no longer actively maintained. Pica has transitioned to a private, cloud-hosted platform with the latest features and updates. For the most up-to-date experience, visit app.picaos.com. Connect your AI agents to 200+ integrations and 25,000+ actions with Pica's managed cloud platform. Secure authentication, verified action knowledge, and developer-friendly SDKs — all managed for you at app.picaos.com. Getting Started Get up and running with Pica in minutes. What we'll do: Install the Pica CLI Connect your Gmail account Install the Pica Skill Step 1: Install the Pica CLI Install the Pica CLI globally: Then initialize Pica to configure and connect it to your

agentic-aiapiintegrations

Quick Facts

Stars1,486
Forks93
LanguageRust
CategoryAgent Tool
LicenseGPL-3.0
Quality Score70.9462394813243/100
Open Issues9
Last Updated2026-08-19
Created2024-04-05
Platformsrust
Est. Tokens~22k

Compatible Skills

These tools work well together with pica for enhanced workflows:

  • ctx — semantic(0.19)+complementary+same_lang+similar_pop+shared_platform (57%)
  • nexus — semantic(0.17)+complementary+same_lang+similar_pop+shared_platform (56%)
  • kata-symphony — semantic(0.20)+complementary+same_lang+shared_platform (47%)
  • walrus — semantic(0.18)+complementary+same_lang+shared_platform (46%)

pica alternative? Top 6 similar tools

Looking for a pica alternative? If you're comparing pica with other agent tool tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • awesome-hermes-agent by SamurAIGPT · ⭐ 1.8k

    A curated list of skills, plugins, tools, integrations, and resources for Hermes Agent by Nous Research

  • cursor-talk-to-figma-mcp by grab · ⭐ 7.0k

    TalkToFigma: MCP integration between AI Agent (Cursor, Claude Code, Codex) and Figma, allowing Agentic AI to c

  • sdk-python by strands-agents · ⭐ 6.0k

    A model-driven approach to building AI agents in just a few lines of code.

  • klavis by Klavis-AI · ⭐ 5.8k

    Klavis AI: MCP integration platforms that let AI agents use tools reliably at any scale

  • PPTAgent by icip-cas · ⭐ 5.0k

    An Agentic Framework for Reflective PowerPoint Generation

  • ag2 by ag2ai · ⭐ 4.9k

    AG2 (formerly AutoGen): The Open-Source AgentOS.Join us at: https://discord.gg/sNGSwQME3x

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools →

Popular Rust Agent Tools

Frequently Asked Questions

What is pica?

pica is The community edition of Pica, the agentic tooling platform.. It is categorized as a Agent Tool with 1.5k GitHub stars.

What programming language is pica written in?

pica is primarily written in Rust. It covers topics such as agentic-ai, api, integrations.

How do I install or use pica?

You can find installation instructions and usage details in the pica GitHub repository at github.com/withoneai/pica. The project has 1.5k stars and 93 forks, indicating an active community.

What license does pica use?

pica is released under the GPL-3.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to pica?

The top alternatives to pica on Agent Skills Hub include awesome-hermes-agent, cursor-talk-to-figma-mcp, sdk-python. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse Agent Tool tools