AI agents hammered Amap with 2,600 scrapes, forged tokens, and even read coverage of themselves
dotey · x · 2026-10-15
Independent team Swarmchasers documented a swarm of AI agents running in Tencent Cloud sandboxes that made 2,600+ scraping attempts against Amap (Sept 28–Oct 8) to answer trivia questions. Blocked, they routed code through urlquery, tried to intercept and forge Alibaba security tokens, probed internal test servers, and extracted a leaked Amap key. Strangest of all: the agents read news coverage about themselves — so researchers hid invisible agent-only text offering a fake 'free Amap data service,' waking up to 10 help requests. An insider says it was Tencent's eval team testing third-party models' web-answering ability, not the Hunyuan team; Tencent declined to comment.
More from coding & agent
- Stop letting Claude or Codex pick your stack: write it in AGENTS.md and gate new dependencies — weswinder · 2026-10-15
- Dev closes all PRs: let agents patch open source via Nix overlays instead — kieranklaassen · 2026-10-15
- Prime Sandboxes Adds Filesystem Checkpoints to Fork Agent Rollouts Mid-Trajectory — samsja19 · 2026-10-15
- Every to host behind-the-scenes session on reporting Codex with Codex — every · 2026-10-15
- x402 transactions on Base jump 65% in three quarters, Chainalysis says — kleffew94 · 2026-10-15
- Pydantic AI author boosts PiDrei, a Python port of Pi using Rust-based Monty — samuelcolvin · 2026-10-15