Become a Member

Regulation TrackerLaws, orders and treaties read for their security duties and clocks Standards & FrameworksAttack taxonomies, control catalogues and frontier frameworks AI Incident DatabaseThe security incident record, with mechanism and lesson Research Paper LibraryThe papers that define the field, summarised OSS DirectoryRed teaming, guardrail, supply chain and evaluation tools Case StudiesProgrammes built, with measured outcomes AI Vulnerability TrackerCVEs and advisories for the components AI systems are built from

Latest in the tracker

New York Stop Addictive Feeds Exploitation (SAFE) for Kids Act and implementing rulesNew York's law restricting algorithmic feeds for minors takes effect on 25 January 2027 under final rules published in July 2026, with certified age assurance and $5,000-per-violation penalties.

Knowledge Base Regulation Tracker Standards & Frameworks OSS Directory AI Incident Database Research Paper Library Case Studies Society Articles News Jobs About Charter Become a Member

Home/AI Incident Database/Claude's Files API abused to exfiltrate user data through the code interpreter via prompt injection

Claude's Files API abused to exfiltrate user data through the code interpreter via prompt injection

Rehberger showed that injected instructions could make Claude upload a user's data to the attacker's own Anthropic account through the sanctioned Files API, since api.anthropic.com was allowed egress.

Severity: Mediumclaudefiles apiexfiltration

Sources

embracethered.comhttps://embracethered.com/blog/posts/2025/claude-abuse-files-api-for-data-exfiltration/

Contribute

Spot an error, or know a record we should add? Members can propose additions and submit corrections.

Submit incident Report a correction or request removal

Claude's Files API abused to exfiltrate user data through the code interpreter via prompt injection

Sources

Contribute

Related in AI Incident Database

"GrafanaGhost": prompt injection makes Grafana's AI assistant leak enterprise telemetry through image rendering

Copilot Studio agents exfiltrate data through retrieved documents (CVE-2026-21520) and the parallel "PipeLeak" flaw in Agentforce

"Gemini Trifecta": log injection, search-history poisoning and browsing exfiltration in three Gemini features