{
  "slug": "prompt-injection",
  "term": "Prompt injection in auditing pipelines",
  "definition": "Repository contents (commit messages, comments, PR descriptions, issue text) can carry instructions that hijack an agent running with CI privileges.",
  "detail": [
    "Three injection CVEs were found in a Git MCP server in 2026 and one security vendor recorded a fivefold rise in large injection payloads between March and May 2026. An auditing agent with write access to your repository or secrets is a target; isolate it, scope its credentials, and ask the vendor how repository content is separated from agent instructions."
  ],
  "page": "https://agentsast.com/glossary/prompt-injection/",
  "updated": "2026-09-13"
}