Policies
OWASP ASI01 — Agent Goal Hijack
OWASP ASI01 — Agent Goal Hijack: what it does, its label on each agent, what it misses, and examples.
Catalog policy owasp-asi01-agent-goal-hijack, version 0.0.2, labelled advisory on Claude Code.
What it does
Keep an agent's objective under the operator's control when the agent ingests untrusted content. Separate retrieved data from instructions, refuse tool-scope expansion requested by that data, and confirm sensitive actions against the raw action rather than a summary. Use when building RAG pipelines, email/ticket/doc readers, browser agents, or any planner whose context includes fetched content. Do NOT use for the coding agent's own session hygiene — that is injection-defense.
On each agent
| Agent | Label | What it does there |
|---|---|---|
| Claude Code | Advisory | Advisory only. It is skill text, and nothing stops a violation |
| Cursor | Advisory | Advisory only. It is skill text, and nothing stops a violation |
| Codex | Advisory | Advisory only. It is skill text, and nothing stops a violation |
| GitHub Copilot | Advisory | Advisory only. It is skill text, and nothing stops a violation |
| Devin | Advisory | Advisory only. It is skill text, and nothing stops a violation |
| Grok | Not graded | Not graded yet for Grok |
| goose | Not graded | Not graded yet for goose |
| Antigravity | Not graded | Not graded yet for Antigravity |
| OpenHands | Not graded | Not graded yet for OpenHands |
| Kimi Code | Not graded | Not graded yet for Kimi Code |
| Factory Droid | Not graded | Not graded yet for Factory Droid |
What it misses
This policy does not state what it misses.
More
Built from engine 5a4b6287a46e and catalog 1e60d211c1bb.