{ "what": "The review queue for openai-chatgpt: one batch a day. Take today's (UTC). The brief: https://newsroom.sgit.ai/reviews/queue/brief.md; the criteria: https://newsroom.sgit.ai/reviews/criteria.md.", "reviewer": "openai-chatgpt", "built": "2026-10-27", "criteria": "v1.2", "batch": 1, "brief": "https://newsroom.sgit.ai/reviews/queue/brief.md", "criteria_md": "https://newsroom.sgit.ai/reviews/criteria.md", "status": "https://newsroom.sgit.ai/reviews/status.json", "days": [ { "date": "2026-10-28", "articles": [ { "slug": "the-ipo-filing-and-the-agents", "title": "The IPO filing and the agents: what Anthropic tells investors about the risks of its own agents, in its own words, and where RiskMandate and Agent Behaviour Policies answer each one", "date": "2026-10-27", "version": "v0.13.99", "hash": "e460b8a399c8", "md": "https://newsroom.sgit.ai/articles/the-ipo-filing-and-the-agents.md", "html": "https://newsroom.sgit.ai/articles/the-ipo-filing-and-the-agents.html", "why": "The editor's priority. Published 27 October; numbers from a filing.", "recheck": [] } ] }, { "date": "2026-10-29", "articles": [ { "slug": "what-the-bitcoin-bounty-actually-proves", "title": "What the $2,000 bitcoin bounty actually proves: php2shell's real timeline, whether a firewall could have seen it coming, and what hardening can and cannot do without the patch", "date": "2026-10-26", "version": "v0.13.97", "hash": "c8f43b81134d", "md": "https://newsroom.sgit.ai/articles/what-the-bitcoin-bounty-actually-proves.md", "html": "https://newsroom.sgit.ai/articles/what-the-bitcoin-bounty-actually-proves.html", "why": "The editor's priority. Published 26 October; a claim about what an event proves.", "recheck": [] } ] }, { "date": "2026-10-30", "articles": [ { "slug": "what-can-your-agent-reach", "title": "What can your agent reach? RiskMandate and the Agent Behaviour Policy, explained for the person who has to decide", "date": "2026-10-18", "version": "v0.12.105", "hash": "65cdbb00cc89", "md": "https://newsroom.sgit.ai/articles/what-can-your-agent-reach.md", "html": "https://newsroom.sgit.ai/articles/what-can-your-agent-reach.html", "why": "The text has changed since your review of 2026-10-18: recheck your findings, then review the rest.", "recheck": [ { "finding": "f1", "issue": "Effective permissions depend on the agent's configured identity and how it is invoked: in chat with User's account, the requester's; in automation, the connection account's, which need not be the rule's creator or the agent's creator; with Agent's account, the agent's own. 'Typically whoever created the rule' implies more than Atlassian documents.", "quote": "Some paths run as somebody else. When a Rovo agent runs from Jira Automation, it uses the permissions of the automation's connection user, typically whoever created the rule", "answer": "fixed", "note": "The identity point is rewritten around Atlassian's identity setting: the requester in chat, the connection account in automation (quoting ROVO-837's 'always use the permissions of the connection user in the automation', since the support-article sentence the review quoted was not found), or the agent's own account; the agent's creator is named as not the deciding identity." }, { "finding": "f2", "issue": "ROVO-837 documents disclosure of a restricted page reference in an automation's output; opening the link still failed. It does not show access to the page or its full content. The reporter notes it does not occur in Rovo Chat.", "quote": "links to pages the triggering user cannot view", "answer": "fixed", "note": "Now says the case disclosed a link to a restricted page, not the page; the link still failed; reading with one identity and publishing to a wider audience is the risk." }, { "finding": "f3", "issue": "Atlassian now documents agents with their own accounts; its 6 October announcement still lists wider agent-account controls and a non-human identity inventory as coming. Availability should be checked per tenant. Agent's-account agents also make content shared with them available to their users.", "quote": "dedicated agent accounts are planned", "answer": "fixed", "note": "Agent accounts described as documented, with the 6 October announcement quoted for the wider controls, a check-your-tenant line, and Atlassian's warning that content shared with such an agent is shared with its users." }, { "finding": "f4", "issue": "The file was less discoverable, not safe; Drive sharing settings still apply.", "quote": "was safe while nobody knew the link", "answer": "fixed", "note": "Now 'hard to find', with 'Google Drive sharing settings still apply.'" }, { "finding": "f5", "issue": "True of Google Drive, not of every connector: synced, direct and Smart Link connectors differ in setup, indexing and authentication.", "quote": "Connectors are set up by an administrator with broad rights, and then each user links their own account", "answer": "fixed", "note": "Now distinguishes synced, direct and Smart Link connectors, quoting Atlassian's connector types page." }, { "finding": "f6", "issue": "Restricting who creates agents (by group) and who uses a particular agent (individuals only) are different controls.", "quote": "administrators can narrow it to selected groups", "answer": "fixed", "note": "Creation by group and use by individual are now separate, with Atlassian's sentence on group restriction not being supported." }, { "finding": "f7", "issue": "Audit logs record events; they do not prevent them. Classification identifies sensitivity and bounds only through a policy acting on it. Only blocking and redaction can prevent data moving.", "quote": "classification, redaction of sensitive data and audit logs, sit in the boundary row too", "answer": "fixed", "note": "The governance tools are now sorted by what each does: blocking and redaction can bound, classification only through a policy, audit logs are evidence, not a barrier." }, { "finding": "f8", "issue": "Indexing allowlists control indexing, not everything Rovo can fetch at run time with the user's access; MCP server permissions govern that server's operations, not every Rovo path, on Atlassian's documentation.", "quote": "The administrator's allowlists for which drives and sites are indexed", "answer": "fixed", "note": "The allowlists are scoped to indexing, and the MCP switches to what the MCP server does, as Atlassian's page states." }, { "finding": "f9", "issue": "The PromptArmor report is accurate as a historical report; present exploitability is unverified.", "quote": "I found no statement from Atlassian on a fix", "answer": "fixed", "note": "Now dated, described as reported as of publication, with current exploitability marked unverified, here and in the limits." }, { "finding": "f10", "issue": "No population evidence for the size of the gap or how often controls are only prompt instructions.", "quote": "for most organisations that is most of the company", "answer": "fixed", "note": "Now 'It can be large, and it has to be measured for the particular deployment rather than assumed'; the earlier 'most organisations' and 'almost nobody' wording is softened." }, { "finding": "f11", "issue": "The library is example policies; connectors to customer systems are built per engagement and none is a product yet.", "quote": "It already covers commercial agents.", "answer": "fixed", "note": "Now 'policies for commercial agents', with RiskMandate's own sentence that no connector is a product yet." }, { "finding": "f12", "issue": "The pricing page marks the £500 and £1,500 levels specified, never run, as of 15 September 2026.", "quote": "from £10 for the pack to £1,500 reviewed", "answer": "fixed", "note": "Now quotes the pricing page's 'specified, never run' for the top two levels, and adds it to the limits." }, { "finding": "f13", "issue": "The merged page documents an external adapter governed by a pinned copy of the evaluator; it does not alter Ruflo's running policy or restrict other shell or MCP tools.", "quote": "enforced it in Ruflo's evaluator, in real time, on every memory operation", "answer": "fixed", "note": "Now scoped to the memory operations of the external adapter, with the page's own statement of what it does not change." }, { "finding": "f14", "issue": "The Northstar results come from a scripted simulation with synthetic cases and no model.", "quote": "overpays $458 in a day; the design with three policies gets all thirteen right", "answer": "fixed", "note": "Now 'thirteen synthetic refund requests', 'a scripted simulation: invented orders, scripted mistakes, no model called', and what it does and does not show." }, { "finding": "f15", "issue": "The Code applies to specified listed companies, not every UK board.", "quote": "Under the UK Corporate Governance Code, boards already have to determine the principal risks", "answer": "fixed", "note": "Now 'For companies the UK Corporate Governance Code applies to'." } ] } ] }, { "date": "2026-10-31", "articles": [ { "slug": "meta-terms-and-the-news", "title": "Meta's new terms and the news: what the crawling clause says, what has happened in five weeks, and why publishers should answer with their own machine-readable terms, not only with letters", "date": "2026-10-27", "version": "v0.13.102", "hash": "489854b7459d", "md": "https://newsroom.sgit.ai/articles/meta-terms-and-the-news.md", "html": "https://newsroom.sgit.ai/articles/meta-terms-and-the-news.html", "why": "Never reviewed by you; never reviewed by anyone.", "recheck": [] } ] }, { "date": "2026-11-01", "articles": [ { "slug": "inside-kitewing-websites", "title": "Inside Kitewing Websites: a made-up studio that sells websites you own, and three made-up client sites built as vault apps, a potter's catalogue, a community garden and a local plumber's guides library, each one file, each different, and each ready to be changed by talking to it", "date": "2026-10-26", "version": "v0.13.96", "hash": "5b59b3afbb7b", "md": "https://newsroom.sgit.ai/articles/inside-kitewing-websites.md", "html": "https://newsroom.sgit.ai/articles/inside-kitewing-websites.html", "why": "Never reviewed by you; never reviewed by anyone.", "recheck": [] } ] }, { "date": "2026-11-02", "articles": [ { "slug": "web-summit-2026-the-plan", "title": "Web Summit 2026, the plan: a briefing for the team on usage first and the sale after, intelligence from public material, an asset, a page and a link for every person we want to reach, a newsroom of our own for the summit, and the two agentic workflows the team will learn on", "date": "2026-10-26", "version": "v0.13.90", "hash": "cee1514801fe", "md": "https://newsroom.sgit.ai/articles/web-summit-2026-the-plan.md", "html": "https://newsroom.sgit.ai/articles/web-summit-2026-the-plan.html", "why": "Never reviewed by you; never reviewed by anyone.", "recheck": [] } ] }, { "date": "2026-11-03", "articles": [ { "slug": "translate-the-assumption", "title": "Translate the assumption, not the vocabulary: Adelina Chalmers' five stages of a CTO's mindset, what they mean for how we brief boards on php2shell, and why a deck for every reader is communication with empathy", "date": "2026-10-25", "version": "v0.13.84", "hash": "8d4d08a6fe0c", "md": "https://newsroom.sgit.ai/articles/translate-the-assumption.md", "html": "https://newsroom.sgit.ai/articles/translate-the-assumption.html", "why": "Never reviewed by you; never reviewed by anyone.", "recheck": [] } ] } ], "remaining": 291, "skeleton": { "schema": "newsroom-review/v1", "criteria": "v1.2", "slug": "", "article_version": "", "article_hash": "", "reviewer": "openai-chatgpt", "kind": "agent", "model": "", "run_by": "", "at": "", "verdict": "", "summary": "", "checks": { "facts": { "result": "not-checked", "notes": "" }, "voice": { "result": "not-checked", "notes": "" }, "claims": { "result": "not-checked", "notes": "" }, "conversions": { "result": "not-checked", "notes": "" }, "health": { "result": "not-checked", "notes": "" }, "people": { "result": "not-checked", "notes": "" } }, "findings": [ { "id": "f1", "criterion": "facts", "severity": "", "section": "", "quote": "", "issue": "", "verification": "", "evidence": "", "source_passage": "", "method": "", "suggestion": "" } ], "verified": [], "not_checked": [] } }