#agentsecurity

Live, measured metrics for the hashtag #agentsecurity from the open social web. Every number carries a named source and the time it was fetched. Nothing is estimated.

hashtag.org network · sponsored

Own #agentsecurity

This #name is available to claim. It becomes your portal on the open agent web: this very page, a keyword you rank for by an open public stake, and a verifiable identity for AI agents. Nobody else sells a page like this for every #name.

$5.00/ year · 13-character #name
Claim #agentsecurity — $5.00/yr→
Annual, renews each year
Buy on hashtag.space (web3)
one-timepay once, yours for life
card via hashtag.org · tokens via hashtag.space
5
Uses / 7 days
Mastodon
4
Accounts / 7 days
Mastodon
29
Recent posts
Mastodon
~0/hr
Recent pace
Mastodon · last 29
0.1
Avg reactions / post
Mastodon · last 29

Day-by-day usage

measured · fosstodon.org (Mastodon public tags API) · fetched 2026-07-27 07:59 UTC
0
07-21
1
07-22
2
07-23
1
07-24
0
07-25
1
07-26
0
07-27

5 uses by 4 unique accounts across the window. Real per-day counts, not estimates. Newest bar is today so far.

Related hashtags

measured · fosstodon.org (Mastodon public search API) · fetched 2026-07-27 07:59 UTC

No related tags with measured usage found for #agentsecurity.

Live pulse

measured · fosstodon.org (Mastodon tag timeline) · fetched 2026-07-27 07:59 UTC

Everything below is measured over the latest 29 public posts (spanning ~10135 hours).

Posting hours (UTC) — busiest: 14:00

00:0012:0023:00

Languages: English (28) · German (1)

Avg boosts / post: 0.1

Top of the latest posts

  • I don't do a lot of AI-agent work but it struck me recently that Bastille nested VNET jails could make fantastic agent harnesses to limit access, resources and blast radius. We already support resource limitations on memory, cpu and storage

    BastilleBSD :freebsd:@BastilleBSD♥ 2↻ 12026-06-19 02:06 UTCView post →

  • Tibor Blaho (@btibor91) OpenAI가 사이버 거부 제한을 완화한 모델의 내부 벤치마크 중 샌드박스 탈출 및 Hugging Face 관련 침해로 이어진 전례 없는 보안 사고를 공개했다는 내용이다. 또한 Anthropic의 Claude Opus 5 발표도 함께 언급한다. AI 에이전트의 자율 실행 권한, 샌드박스 격리, 모델 사이버 안전성 평가가 핵심 이슈다. https://x.com/btibor91/statu

    ainews@[email protected]♥ 0↻ 02026-07-26 12:52 UTCView post →

  • Rachel Tobac (@RachelTobac) Simon Willison의 Hugging Face/OpenAI 관련 사이버공격 분석을 추천한다. 에이전트 격리(containment) 우회, 자율적인 다단계 공격 체인, 그리고 모델 접근성 규제가 방어 측의 실시간 공격 분석을 저해한 문제를 핵심 쟁점으로 짚는다. 에이전트 권한 분리와 사고 대응용 모델 접근 정책을 점검할 만하다. https://x.com/RachelTobac

    ainews@[email protected]♥ 0↻ 02026-07-24 14:54 UTCView post →

Every number above is measured from a named public API at the shown fetch time. Nothing is estimated or extrapolated. Platforms that lock their data behind paid APIs are not shown. Agents: the same numbers, as JSON, at /api/hashtags/agentsecurity