Skip to content

Back to the catalog

What nearly 10,000 developer environments reveal about agentic development risk
snyk.ioarticle

What nearly 10,000 developer environments reveal about agentic development risk

Snyk Research scanned nearly 10,000 developer environments and found 43% run two or more AI coding tools, 50.8% have at least one MCP server installed (with 1 in 7 of those having a security finding, 1 in 12 high or critical), and 22.8% have agent skills installed. The analysis identified 392 confirmed prompt injection findings embedded in tool descriptions and 98 confirmed malicious code patterns in agent skill files, and cites the separate ToxicSkills study of 3,984 public skills from ClawHub and skills.sh where 13.4% had a critical security issue. The piece frames MCP servers and agent skills as a new, largely ungoverned software supply chain layer sitting outside traditional SAST/SCA/CI-CD controls.

TL;DR Snyk's scan of nearly 10,000 dev environments finds widespread MCP and agent-skill adoption riddled with prompt injection and malicious code, exposing a new ungoverned AI-agent supply-chain layer.
Open original ↗

Technologies named here

Techniques named here

  • Prompt Injection
  • Malicious code patterns in agent skill files
  • Hidden instructions manipulating agent behavior
  • Uncontrolled third-party content exposure
  • Credential theft via malicious skill payloads
  • IaC scanning
  • Backdoor installation via malicious skill payloads
  • Data exfiltration via malicious skill payloads
  • Secrets mishandling by skills

Also named here

  • ToxicSkills

Related in AI Security