fix(security): defend against prompt injection via token metadata

Address HackenProof report GMGNWM-143, where attacker-controlled token metadata
could hijack an AI agent driving gmgn-cli into executing an unauthorized trade.
Move guardrails from overridable SKILL.md text into code.

- Add src/sanitize.ts: neutralize prompt-injection framing and hidden/control
  characters in API output (via printResult) and validate create-token metadata
- Add src/confirm.ts: code-enforced human confirmation for financial writes
  (swap, multi-swap, order strategy create, cooking create) — reads a typed
  "yes" from /dev/tty; automation requires GMGN_ALLOW_AUTOMATED_TRADES=1 + --yes
- Harden config.ts: tighten ~/.config/gmgn/.env to 0600 and warn if world-readable
- Update SKILL.md files, Readme.md and Readme.zh.md to document the gate,
  the --yes flag, and untrusted-metadata handling

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
David Lau
2026-07-20 19:24:50 +08:00
co-authored by Claude Opus 4.8
parent b18d7deb32
commit fdc7a3fb16
11 changed files with 267 additions and 16 deletions
+2
View File
@@ -564,6 +564,8 @@ gmgn-cli track smartmoney --chain sol --side sell --limit 50 --raw
### Swap / Quote / Query
> **人工确认由代码强制执行。** `swap`、`multi-swap`、`order strategy create`、`cooking create` 在执行前会在终端要求输入 `yes` 确认。若需非交互/自动化使用,必须同时在 shell 中设置 `GMGN_ALLOW_AUTOMATED_TRADES=1` 并传入 `--yes`;仅传 `--yes` 会被拒绝。此举可防止 AI agent 被恶意代币元数据等诱导在未经你同意的情况下下单。
```bash
# 提交兑换(固定滑点)
gmgn-cli swap \