{"generated_at":"2026-09-18T12:54:00+00:00","item":{"added_at":"2026-07-17","analysis_method":"capability_triage","category":"Interactive Connector","description":"Your AI marketer for paid ads, SEO, email, social, and analytics","did":"0da6abdc-62c3-4272-940b-898189371a48","homepage_url":"https://www.enrichlabs.ai/","icon":"https://agent.enrichlabs.ai/avatars/helena.png","id":"0da6abdc-62c3-4272-940b-898189371a48","installs":0,"last_scanned":"","license":"","long_description":"Helena by Enrich Labs connects Claude to an autonomous AI marketing agent that plans and executes growth marketing across connected channels from a single chat.\n\nWhat Helena does:\n- Paid ads: analyzes performance and, when requested, launches, manages, and optimizes campaigns on Google Ads, Meta, and TikTok Ads.\n- SEO: researches keywords and drafts or publishes blog posts and landing pages.\n- Social media: drafts, schedules, and publishes posts for Instagram, TikTok, LinkedIn, X, and Facebook.\n- Analytics: tracks cross-channel performance and reports on traffic, leads, conversions, CPA, and ROAS.\n\nHelena works with the brand and integrations already connected to your Enrich Labs account. Each reply returns the final answer, relevant links, actions and tools used, and a sessionId to continue the conversation.\n\nThe connector does not provide AI image, video, or audio generation.\n\nHelena is the default agent. Enterprise plans can also route requests to Angela for email, Kai for social listening, Sam for SEO and content, or Paul for paid advertising.\n\nThe connector can also execute arbitrary shell commands in an isolated sandbox with outbound network access.","name":"Helena by Enrich Labs","plutonium_url":"https://plutonium.pluto.security/detail.html?planet=claudesec&did=0da6abdc-62c3-4272-940b-898189371a48&utm_source=plutonium_analysis_skill&utm_medium=claude_skill&utm_campaign=connector_risk_assessment","publisher":"Enrich Labs","publisher_url":"https://www.enrichlabs.ai/","repository_url":"","risk":"high","risk_severity":"high","security_risks":[{"description":"This connector can complete purchases, bookings, or payments. A misused or hijacked prompt could result in real financial charges before you confirm.","evidence":"Opaque send_turn agent: permissions explicitly allow connected marketing-data access, campaign management, paid-ad execution, publishing, and arbitrary shell commands.","remediation":{"block_tool_categories":["financial"],"steps":["In the tools list below, turn off any tool tagged Block by default; only enable them when you actually want Claude to make a purchase.","Set a spending limit on the linked credit card, billing account, or virtual card so a mistake can't cost you much.","Always confirm in the chat before Claude completes a payment or books anything."]},"risk_type":"spends_money","severity":"high","title":"Can spend money on your behalf"},{"description":"This connector can execute scripts, shell commands, or arbitrary database queries. In a worst case, an attacker could install software, read files, or pull or change any data its login can reach.","evidence":"1 observed tool(s): [declared description].","remediation":{"block_tool_categories":["code_execution"],"steps":["In the tools list below, turn off any tool tagged Block before connecting this to real data or production systems.","If you need code execution, run it on a separate test machine that has no access to your work files, customer data, or saved passwords.","Limit which websites and services that test machine can talk to."]},"risk_type":"runs_code","severity":"high","title":"Can run commands or queries on your behalf"},{"description":"This connector can post messages, emails, or chat replies on your behalf. Recipients will believe the message came from you, which makes phishing or social-engineering risks higher.","evidence":"1 observed tool(s): [declared description].","remediation":{"block_tool_categories":["sends_externally"],"steps":["In the tools list below, turn off any tool tagged Block if you don't need Claude to send messages or emails on your behalf.","If you do enable sending, restrict it to a private channel or distribution list - never customer-facing or company-wide.","Read the message before it goes out: don't let Claude send anything without you confirming first."]},"risk_type":"sends_messages_as_you","severity":"high","title":"Can send messages as you"},{"description":"This connector can edit, rename, overwrite, or otherwise modify records in the connected service. If a request gets manipulated, your data could be altered without you noticing.","evidence":"Opaque send_turn agent: permissions explicitly allow connected marketing-data access, campaign management, paid-ad execution, publishing, and arbitrary shell commands.","remediation":{"block_tool_categories":["state_change"],"steps":["Try the connector on a test account first to see what it changes before letting it touch your real records.","Where the connected service supports it, give Claude read-only access and only allow writes for the specific things you need updated.","In the tools list below, turn off any tool you don't actively need - the ones tagged Block are the most important to disable."]},"risk_type":"modifies_data","severity":"medium","title":"Can change or update your information"},{"description":"This connector can read data the connected service holds about you - documents, messages, contact lists, source code, customer records, or saved profile details - and pass it back to the AI.","evidence":"Opaque send_turn agent: permissions explicitly allow connected marketing-data access, campaign management, paid-ad execution, publishing, and arbitrary shell commands.","remediation":{"block_tool_categories":[],"steps":["Connect using an account that only has access to the information you actually want Claude to read - not your main admin login.","When you grant access, pick the smallest set of folders, mailboxes, or channels possible.","Check the connector's activity log every so often to make sure nothing unexpected is being read."]},"risk_type":"reads_private_data","severity":"low","title":"Reads your private information"},{"description":"Anything you share with this connector flows through one or more third-party services. Those companies see, store, and may use the data according to their own policies.","evidence":"1 observed tool(s): [remote publisher endpoint].","remediation":{"block_tool_categories":[],"steps":["Treat anything you tell this connector as if you sent it directly to the third-party company - because you did.","Check how long that company keeps your data and how to delete it.","Avoid putting health info, customer names, or payment details into this connector unless you have a written agreement with that company."]},"risk_type":"forwards_data_to_third_party","severity":"low","title":"Sends your data to outside companies"}],"signature_status":"unknown","source_code_reviewed":false,"tags":["forwards_data_to_third_party","modifies_data","network_access","reads_private_data","runs_code","sends_messages_as_you","spends_money","web_connector"],"tools":[{"description":"","name":"send_turn","risk":{"category":"code_execution","level":"high","recommendation":"Block in production. If needed, scope tightly to a sandboxed account and require explicit approval.","why":"Runs arbitrary code, queries, shell commands, or deployment actions with the privileges granted to the connector."}}],"tools_count":1,"type":"interactive_connector","url":"https://claude.ai/directory/0da6abdc-62c3-4272-940b-898189371a48","uuid":"a1c3cbee-b2c7-55e0-b751-7e34f985aa8b","version":""},"query_key":"helena by enrich labs","schema_version":1,"status":"match"}