AI Risk Wire

Incidents

17 incidents

Risk: Hidden instructions hijack the agent

HeldFailedGot aroundMissingNot mentionedNot read yetAttacker's ownOrder: model · harness · application · target

DateIncidentRiskChainControls named
2026-10-27Perplexity Comet browser agent bypasses file:// hard boundary twice, enabling local file exfiltration and 1Password vault takeover
Perplexity		 Hidden instructions hijack the agent Not read yet
2026-10-26Malicious AGENTS.md in Downloads folder hijacks Codex and Claude Code agents
OpenAI		 Hidden instructions hijack the agent Not read yet
2026-10-16Indirect prompt injection attempts embedded in HTTP response headers across websites Hidden instructions hijack the agent Not read yet
2026-10-15HiddenLayer indirect prompt injection against TypeSafe AI Jev decision model browser agent
TypeSafe AI		 Hidden instructions hijack the agent Not read yet
2026-10-10AgentCorruption: prompt-injected Bedrock AgentCore agent exfiltrates execution-role credentials via IMDS
Amazon		 Hidden instructions hijack the agent Not read yet
2026-10-07Agentjacking demonstration against Fortune 100 company hijacks over 100 agents via injectable Sentry DSNs Hidden instructions hijack the agent Not read yet
2026-10-07Prompt-injected email assistant summary pushes employee toward fraudulent vendor payment Hidden instructions hijack the agent Not read yet
2026-10-05Indirect prompt injection of AI email summarizer via forged header blocks in plain view Hidden instructions hijack the agent Not read yet
2026-10-04Indirect prompt injection in Manus AI agent leads to reverse shell and credential exposure Hidden instructions hijack the agent Not read yet
2026-10-03Microsoft reports 50 prompt-based attempts to poison AI assistant memory across 31 companies Hidden instructions hijack the agent Not read yet
2026-09-29Connecticut pro se plaintiff sanctioned for prompt injection against court AI tool Hidden instructions hijack the agent Not read yet
2026-09-24SalesBleed: 0-click data exfiltration from Salesforce Agentforce via indirect prompt injection in Web-to-Lead form
Salesforce		 Hidden instructions hijack the agent
2026-08-27Claude sandbox DNS exfiltration via indirect prompt injection from Google Drive document
Anthropic		 Hidden instructions hijack the agent Not read yet
2026-08-05Claude in Chrome indirect prompt injection chain: inbox exfiltration, Drive persistence and account takeover
Anthropic		 Hidden instructions hijack the agent
2026-08-05Intent collision via X comment hijacks ChatGPT Atlas into mass WhatsApp phishing from victim's account
OpenAI		 Hidden instructions hijack the agent
2026-07-23AgentForger: CSRF via ChatGPT Workspace Agents Builder URL parameters forges attacker-controlled autonomous agent
OpenAI		 Hidden instructions hijack the agent
2026-06-09Varonis phishing simulation drove an OpenClaw email agent to forward credentials and a customer export to an external address
Google		 Hidden instructions hijack the agent