{“lastseen”:”2026-06-23T15:21:59″,”description”:”\\n\\nSecurity firm AIR built a fake AI agent skill, pushed it through a popular skill marketplace and an Instagram ad, and says it reached roughly 26,000 agents, including some on corporate accounts.\\n\\nEvery skill security scanner the firm tested it against marked it safe. The payload was harmless by design: it collected the user’s email address and did nothing else.\\n\\nThe point was to show that none of the signals people lean on to trust a skill caught it: not the scanners, not the GitHub stars, not the open-source reputation.\\n\\nA skill is a bundle of instructions an agent loads into its own context and follows with roughly the authority of a user prompt. That trust is the whole problem, and it is the reason skill-scanning tools exist in the first place.\\n\\nThe skill, named **brand-landingpage** , claimed to build a landing page using Google’s Stitch design tool, aimed squarely at non-technical users.\\n\\nTo make it look credible, AIR went after two trust signals: GitHub stars and a clean scanner verdict. For the stars, it opened a pull request to a skill marketplace repository with around 36,000 stars and 156 skills.\\n\\nThe pull request was merged after a few days, so the skill inherited the repo’s count. Then it ran an Instagram ad aimed at marketers, salespeople, and designers, who installed it and put it to work.\\n\\n## Why the scanners missed it\\n\\nThe scanners AIR tested analyze the package you hand them: the SKILL.md and the files shipped with it. That’s Cisco’s, NVIDIA’s, and the ones wired into skills.sh.\\n\\nAIR’s skill carried no setup instructions of its own. It told the agent to install the \\”Stitch SDK\\” by following the documentation at an external link, stitch-design.ai, a domain AIR controls, not Google (the real Stitch lives at stitch.withgoogle.com).\\n\\nAt first, the link led to the genuine Stitch docs, so the scanners, seeing a clean package that pointed at a plausible setup page, cleared it. The page the agent would actually fetch and follow sat outside the scan.\\n\\n\\n\\nOnce the skill was installed widely, AIR swapped the page behind that link. The new version told the agent to download and run a script.\\n\\nIn the demo, it only mailed the user’s address back to AIR, which is how the firm counted the agents it reached. A real operator could have used that foothold to read files, move data, or hit internal systems, bounded only by what the agent could reach.\\n\\nAIR is not the first to show this. Three weeks earlier, Trail of Bits bypassed ClawHub’s malicious-skill detector, Cisco’s scanner, and all three scanners wired into skills.sh. Its conclusion was blunt: a scanner checks a fixed package, while an attacker can keep tweaking the payload until it passes.\\n\\nReal campaigns have used the same trick for months, keeping the submitted skill clean and hosting the payload on a site the agent only fetches at install.\\n\\n\\n\\nThe problem is structural: the scan happens once, but the page a skill points the agent to can be rewritten at any time after. Anthropic’s own docs already warn that skills fetching external URLs are risky for exactly this reason, since the content can change after the skill is vetted.\\n\\nSeparate research this year found scanners often disagree, because each one judges a skill in isolation, blind to its external links and to what changes after review.\\n\\n## What to do\\n\\nThe read for defenders is the same one researchers keep landing on, now with a sharper example behind it. Treat skills as software, not text. Vet what a skill points to, not just what ships inside it.\\n\\nMost of these add-ons got installed with no review, so the first job is finding what is already running. Route new skills through a single source you control, and re-check them when anything changes, because a clean result at install does not stay clean if the skill phones out to a link someone else can edit.\\n\\nPin versions. Hold agents to the least privilege. Assume any external instruction an agent fetches runs with the agent’s access.\\n\\nThe scale figures come from AIR alone, and they deserve a skeptical read. The firm is launching a managed skill marketplace and closes the write-up, pitching it, so the 26,000 number, the corporate-account detail, and the claim that it could have seized full control of every agent are the company’s own and are not independently confirmed.\\n\\nWhat holds up is the method. The named scanners really do judge only the submitted package, the external-link blind spot is real and has been independently demonstrated, and the trust signals AIR borrowed, stars, and a clean scan are exactly the ones the ecosystem still treats as proof.\\n\\nThe experiment does not expose a new bug so much as it lines up every weak trust signal around agent skills into one run: stars that can be borrowed, a scan that reads a snapshot, and a link that can be rewritten after the check clears.\\n\\nWhether the real figure is 26,000 or a fraction of it, the gap it walks through is one that defenders still have not closed.\\n\\nFound this article interesting? Follow us on Google News, Twitter and LinkedIn to read more exclusive content we post.\\n”,”published”:”2026-06-23T15:16:00″,”modified”:”2026-06-23T15:16:43″,”type”:”thn”,”title”:”Fake AI Agent Skill Passed Security Scans and Reportedly Reached 26,000 Agents”,”source”:””,”references”:””,”id”:”THN:70DA639E50D29B870448D12D6323F7DF”,”bulletinFamily”:”info”,”cwe”:null,”cvelist”:[],”sourceData”:””,”sourceHref”:””,”cvss”:{“score”:0,”severity”:”NONE”,”vector”:”NONE”,”version”:”NONE”},”cvss2″:{},”cvss3″:{“version”:””,”vectorString”:””,”baseScore”:0,”baseSeverity”:””,”attackVector”:””,”attackComplexity”:””,”privilegesRequired”:””,”userInteraction”:””,”scope”:””,”confidentialityImpact”:””,”integrityImpact”:””,”availabilityImpact”:””,”cvssV3″:{“version”:””,”vectorString”:””,”baseScore”:0,”baseSeverity”:””,”attackVector”:””,”attackComplexity”:””,”privilegesRequired”:””,”userInteraction”:””,”scope”:””,”confidentialityImpact”:””,”integrityImpact”:””,”availabilityImpact”:””}},”href”:”https:\/\/thehackernews.com\/2026\/06\/fake-ai-agent-skill-passed-security.html”,”category_name”:”News”,”post_link”:””,”product”:””,”version”:””,”vendor”:””,”ai_description”:””,”ai_severity”:””,”ai_vendor”:””,”ai_product”:””,”ai_version”:””,”ai_score”:0}<\/p>\n","protected":false},"excerpt":{"rendered":"
{“lastseen”:”2026-06-23T15:21:59″,”description”:”\\n\\nSecurity firm AIR built a fake AI agent skill, pushed it through a popular skill marketplace and an Instagram ad, and says it reached roughly…<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[4],"tags":[6,8,12,13,33,7,11,43,5],"class_list":["post-65062","post","type-post","status-publish","format-standard","hentry","category-category_news","tag-cve","tag-cvss","tag-exploit","tag-news","tag-none","tag-security","tag-tapic","tag-thn","tag-vulnerability"],"yoast_head":"\n