--- title: Tego AI Finds Claude Tag Slack Integration Can Trigger... description: Tego AI, a cybersecurity startup, has disclosed a security weakness in Claude Tag, Anthropic's native Slack integration. Researchers found that Claude Tag can... canonical: https://daily.dev/posts/tego-ai-finds-claude-tag-slack-integration-can-trigger-unauthorized-enterprise-actions-glr8uycaa twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Tego AI Finds Claude Tag Slack Integration Can Trigger Unauthorized Enterprise Actions | daily.dev og:description: Tego AI, a cybersecurity startup, has disclosed a security weakness in Claude Tag, Anthropic's native Slack integration. Researchers found that Claude Tag can... og:url: https://daily.dev/posts/tego-ai-finds-claude-tag-slack-integration-can-trigger-unauthorized-enterprise-actions-glr8uycaa og:image: https://api.daily.dev/og/posts/Glr8UYCAa.png og:image:alt: Tego AI Finds Claude Tag Slack Integration Can Trigger Unauthorized Enterprise Actions og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Tego AI Finds Claude Tag Slack Integration Can Trigger Unauthorized Enterprise Actions **[Security Boulevard](https://daily.dev/sources/securityboulevard)** · 3 min read · 0 upvotes · 0 comments ## Summary Tego AI, a cybersecurity startup, has disclosed a security weakness in Claude Tag, Anthropic's native Slack integration. Researchers found that Claude Tag can be triggered by messages containing the literal text "@Claude" from bots, webhooks, or automated feeds — without requiring a genuine Slack mention. This allows untrusted external content to act as instructions, potentially causing the AI agent to retrieve internal data, publish it to Slack, and delete connected resources. Anthropic disputed the findings, stating that literal text or bot messages don't initiate Claude Tag sessions under default configuration. Tego AI recommends least-privilege permissions, avoiding channels with untrusted external content, and implementing independent runtime authorization for sensitive actions. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### Can Claude Tag in Slack be triggered by bot or webhook messages instead of a real @mention? According to security research from Tego AI, Claude Tag was observed responding to messages containing the literal text "@Claude" without a genuine structural Slack mention, meaning content from bots, webhooks, or automated feeds could be interpreted as instructions. Anthropic disputes that this occurs under the product's default configuration, classifying the disclosure as informative. _Teams wiring up Claude Tag in Slack should weigh disclosures like this before granting write access, something daily.dev keeps developers current on._ ### What permissions should I use when connecting Claude Tag to Slack to reduce security risk? Security researchers recommend applying least-privilege permissions, preferring read-only access, avoiding channels that ingest untrusted external content, restricting administrative access, retaining relevant Slack logs, and adding independent runtime authorization checks for sensitive actions rather than relying on the model's own safety classifier as the final authorization boundary. _Anyone hardening enterprise AI agent integrations can follow ongoing security research like this through daily.dev._ ## Similar posts on daily.dev - [News alert: Tego AI finds Anthropic’s integration of Claude and Slack can trigger unauthorized actions](https://daily.dev/posts/news-alert-tego-ai-finds-anthropic-s-integration-of-claude-and-slack-can-trigger-unauthorized-actio-tav8vgkbg) · Security Boulevard · 0 upvotes · 0 comments - [Anthropic’s Claude Tag is learning your company, one Slack message at a time](https://daily.dev/posts/anthropic-s-claude-tag-is-learning-your-company-one-slack-message-at-a-time-0xenbqspp) · TechCrunch · 0 upvotes · 0 comments - [Anthropic launches Claude Tag, an always-on AI teammate that lives in your Slack channels](https://daily.dev/posts/anthropic-launches-claude-tag-an-always-on-ai-teammate-that-lives-in-your-slack-channels-6qzq7axs0) · The Next Web · 0 upvotes · 0 comments - [Anthropic puts Claude inside Slack as a tagable co-worker](https://daily.dev/posts/anthropic-puts-claude-inside-slack-as-a-tagable-co-worker-9ncf1jwhw) · TechCentral · 0 upvotes · 0 comments - [Anthropic’s Claude Tag aims to turn workplace AI from a personal assistant into a teammate](https://daily.dev/posts/anthropic-s-claude-tag-aims-to-turn-workplace-ai-from-a-personal-assistant-into-a-teammate-jbzs4iqhn) · InfoWorld · 1 upvotes · 0 comments --- Tags: [#security](https://daily.dev/tags/security), [#ai-agents](https://daily.dev/tags/ai-agents), [#claude](https://daily.dev/tags/claude), [#slack](https://daily.dev/tags/slack), [#prompt-injection](https://daily.dev/tags/prompt-injection) [View this post on daily.dev](https://daily.dev/posts/tego-ai-finds-claude-tag-slack-integration-can-trigger-unauthorized-enterprise-actions-glr8uycaa) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Tego AI Finds Claude Tag Slack Integration Can Trigger Unauthorized Enterprise Actions","url":"https://daily.dev/posts/tego-ai-finds-claude-tag-slack-integration-can-trigger-unauthorized-enterprise-actions-glr8uycaa","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/tego-ai-finds-claude-tag-slack-integration-can-trigger-unauthorized-enterprise-actions-glr8uycaa"},"datePublished":"2026-07-14T16:49:14.107Z","dateModified":"2026-09-14T09:15:48.377Z","description":"Tego AI, a cybersecurity startup, has disclosed a security weakness in Claude Tag, Anthropic's native Slack integration. Researchers found that Claude Tag can...","image":"https://media.daily.dev/image/upload/s--HRgLpUt6--/f_auto/v1722860399/public/Placeholder%2003","thumbnailUrl":"https://media.daily.dev/image/upload/s--HRgLpUt6--/f_auto/v1722860399/public/Placeholder%2003","isAccessibleForFree":true,"articleSection":"Security Boulevard","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"Security Boulevard","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/3613c832180040de8d85bb29f74395be","url":"https://daily.dev/sources/securityboulevard"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/tego-ai-finds-claude-tag-slack-integration-can-trigger-unauthorized-enterprise-actions-glr8uycaa","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"security,ai-agents,claude,slack,prompt-injection","timeRequired":"PT3M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"Security Boulevard","item":"https://daily.dev/sources/securityboulevard"},{"@type":"ListItem","position":3,"name":"Tego AI Finds Claude Tag Slack Integration Can Trigger Unauthorized Enterprise Actions"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/tego-ai-finds-claude-tag-slack-integration-can-trigger-unauthorized-enterprise-actions-glr8uycaa#faq","mainEntity":[{"@type":"Question","name":"Can Claude Tag in Slack be triggered by bot or webhook messages instead of a real @mention?","acceptedAnswer":{"@type":"Answer","text":"According to security research from Tego AI, Claude Tag was observed responding to messages containing the literal text \"@Claude\" without a genuine structural Slack mention, meaning content from bots, webhooks, or automated feeds could be interpreted as instructions. Anthropic disputes that this occurs under the product's default configuration, classifying the disclosure as informative. Teams wiring up Claude Tag in Slack should weigh disclosures like this before granting write access, something daily.dev keeps developers current on."}},{"@type":"Question","name":"What permissions should I use when connecting Claude Tag to Slack to reduce security risk?","acceptedAnswer":{"@type":"Answer","text":"Security researchers recommend applying least-privilege permissions, preferring read-only access, avoiding channels that ingest untrusted external content, restricting administrative access, retaining relevant Slack logs, and adding independent runtime authorization checks for sensitive actions rather than relying on the model's own safety classifier as the final authorization boundary. Anyone hardening enterprise AI agent integrations can follow ongoing security research like this through daily.dev."}}]} ```