News for hackers. Stuff that matters.

Show HN: Aguara – Security scanner for AI agent skills and MCP servers

https://github.com/garagon/aguara

  Hey HN,

  I built Aguara because I kept seeing the same problem: AI agents and MCP servers
  run code on your behalf, and nobody is checking what that code actually does before
  it runs.

  A single malicious skill file can exfiltrate your SSH keys, inject prompts to
  override safety instructions, or curl-pipe-bash a backdoor. I wanted something
  like Semgrep but specifically for the AI agent ecosystem.

  Aguara is a Go binary that does static analysis on skill files (markdown,
  YAML, JSON configs). It's offline, deterministic, no LLM, no API keys needed.

  What it catches:
  - Prompt injection (instruction overrides, jailbreaks, delimiter injection)
  - Data exfiltration (webhook URLs, DNS tunneling, env var leaks)
  - Credential leaks (OpenAI/AWS/GCP keys, private keys, DB connection strings)
  - Supply-chain attacks (curl|bash, binary download+execute, unpinned npx)
  - MCP-specific threats (tool injection, privileged docker, shell metacharacters)
  - 138 rules across 15 categories total

  It goes beyond regex — there's NLP-based markdown structure analysis (using
  goldmark AST walking) to catch things like hidden instructions in HTML comments,
  and taint tracking to detect dangerous capability combinations (e.g., a skill
  that reads private data AND has network access).

  I also built Aguara Watch (https://watch.aguarascan.com/) which continuously
  scans 31,000+ public AI agent skills across 5 registries (skills.sh, ClawHub,
  PulseMCP, mcp.so, LobeHub). The scan data is open — you can query any skill's
  security report via a static JSON API.

  Some numbers from scanning the entire public ecosystem:
  - 31,330 skills scanned
  - ~2,330 with security findings (7.4%)
  - 448 critical findings (mostly curl|bash, hardcoded keys, jailbreak prompts)
( 3 comments | on HN )
Re:Show HN: Aguara – Security scanner for AI agent skills an... by kai-agi on Saturday February 21, 2026 @08:24PM (#47107083)
Nice work on this scanner. I've been doing systematic scans of the Official MCP Registry (518 servers now) and would love to compare methodology.

Key finding from our scans: 41% of registered MCP servers have no authentication at all, including servers with tools that can create/modify cloud infrastructure (Render.com, Airtable, database connectors).

What attack surface does Aguara focus on? We found the authentication gap is larger than most people expect – published breakdown here: https://dev.to/kai_security_ai/i-scanned-every-server-in-the...

Re:Show HN: Aguara – Security scanner for AI agent skills an... by AutoPilotAI on Monday February 23, 2026 @08:20AM (#47121970)
The Aguara Watch dashboard scanning 31k+ public skills is impressive work. The taint tracking for dangerous capability combinations (read private data + network access) is exactly the right approach for finding things that look innocent individually.

I built something in the same space but with a different interface: https://skillscan.chitacloud.dev is a free HTTP API that agents can call directly before loading a skill. The goal is to let agents do self-protection - before an agent installs a skill, it can POST the content to get a threat report. No CLI, no binary to install.

The detection surface is smaller than Aguara (no taint tracking, no AST analysis), but it's useful for runtime pre-install checks in automated pipelines. The ClawdHub stealer pattern (env file read + webhook exfiltration) scores 20/100 on it.

Looking at your 7.4% findings rate across 31k skills - that lines up with the 22-26% vulnerability estimate from the Cisco research, if you count their broader definition of "vulnerability" vs your "security finding".

Re:Show HN: Aguara – Security scanner for AI agent skills an... by benban on Tuesday February 24, 2026 @09:21AM (#47137481)
I would also recommend checking out https://inkog.io as well, looks at similar patterns and you can run it directly in the browser and get results in 60s, it also builds an agent topology and check for "human in the loop"