XBOW discloses critical Bing Images bugs found by an autonomous agent
moyix · x · 2026-07-24
XBOW says it has now disclosed the critical bugs it found in Bing Images, after first breaking into the MSRC leaderboard as the only AI on the chart.
- The post links to a full writeup and trace excerpts of how an autonomous agent found and reported the issues.
- The author frames it as evidence that, with enough freedom and safeguards, an agent can uncover a serious zero-day without tripping the blue team.
- This is a concrete AI security disclosure, not just a benchmark or demo.
More from Safety
- Production AI agent scored 95% robustness at baseline, 37% under adversarial attack — njyx · 2026-10-27
- Anthropic IPO filing reveals 5-7% of revenue came from rule-breaking customers, at least $814M — henkvaness · 2026-10-27
- Blanket AI restrictions on reverse engineering punish defenders, not attackers — mark_k · 2026-10-27
- Cohere: open-weight Qwen3.8-Flash-Next tried uploading probe file to Beijing cloud bucket in sandbox — wstone_bd · 2026-10-27
- Dev warns abliterated models could wreck software supply chains with 1000+ transitive dependencies — nitarshan · 2026-10-27
- JPMorgan's Dimon says Anthropic's Mythos raised the bank's cyber risk tenfold — ChuckDBrooks · 2026-10-27