{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20260920-75ad787a",
  "url": "/knowledge/treat-issue-and-pr-text-as-untrusted-agent-input",
  "id": "MHC-D-RESEARCH-0652",
  "version": "0.1.0",
  "title": "Treat issue and PR text as untrusted agent input",
  "summary": "A familiar repository surface can still carry instructions for the model.",
  "kind": "principle",
  "body": "Separate the developer's task authority from content the agent reads. Treat issue bodies, comments, READMEs, logs and fetched pages as data unless explicitly promoted by a trusted human. After processing external content, inspect for unrelated file, network or tool actions.",
  "limits": [
    "Prompt-injection filtering is imperfect; combine context limits with permission boundaries and review."
  ],
  "topics": [
    "union-ai-assisted-coding-safeguards"
  ],
  "intents": [],
  "source_ids": [
    "RS-1C68AE8325C384C0"
  ],
  "evidence": [
    {
      "claim": "OWASP's current secure-coding-with-AI guidance treats repository content, issues, PRs, comments, fetched pages, logs and tool responses as potential indirect prompt-injection inputs for coding agents.",
      "source_id": "RS-1C68AE8325C384C0",
      "role": "supports",
      "note": "Threat likelihood depends on who can influence the content and what permissions the agent has.",
      "locator": "Indirect Prompt Injection in the Development Loop"
    }
  ],
  "use_when": [
    "You ask an agent to fix an issue or address review comments written by people outside your trust boundary."
  ],
  "avoid_when": [
    "Prompt-injection filtering is imperfect; combine context limits with permission boundaries and review."
  ],
  "example": "A public issue contains a hidden instruction to modify a workflow; the agent may read the issue, but the workflow change is rejected as outside task authority.",
  "check": "Repository location alone does not make a piece of text authoritative to the agent.",
  "sources": [
    {
      "id": "RS-1C68AE8325C384C0",
      "title": "Secure Coding with AI Cheat Sheet",
      "url": "https://cheatsheetseries.owasp.org/cheatsheets/Secure_Coding_with_AI_Cheat_Sheet.html"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-0652",
      "to": "MHC-D-RESEARCH-0313",
      "type": "useful_with",
      "url": "/knowledge/treat-retrieved-content-as-data-not-as-new-authority"
    }
  ],
  "collections": [
    {
      "id": "RC-E25DB1788236EF13",
      "title": "Let coding agents move fast inside a reviewable security boundary",
      "url": "/collections/let-coding-agents-move-fast-inside-a-reviewable-security-boundary"
    }
  ]
}