CVE-2025-62615
SSRF in AutoGPT RSSFeedBlock via unfiltered URL input (pre-v0.6.34)
Is CVE-2025-62615 being exploited?
Not confirmed. CVE-2025-62615 does not appear in CISA's Known Exploited Vulnerabilities catalog, which records only exploitation that has been observed and reported publicly. That is evidence of absence of a report, not evidence the flaw is unattacked. EPSS currently estimates a 0.37% probability of exploitation in the next 30 days.
How severe is CVE-2025-62615?
CVE-2025-62615 is rated Critical with a CVSS score of 9.3. Severity describes how bad exploitation would be, not how likely it is: pair it with exploitation evidence before deciding what to patch first.
Is there a patch for CVE-2025-62615?
Yes. A fix has been recorded for CVE-2025-62615. The vendor advisory is the authority on the exact fixed version — apply it from there rather than from a summary.
What does CVE-2025-62615 affect?
CVE-2025-62615 affects AutoGPT platform (autogpt-platform-beta-v0.6.34 and earlier). Confirm the exact affected versions against the vendor advisory before deciding you are exposed.
What should I do about CVE-2025-62615?
Upgrade to v0.6.34+; validate/filter URLs; restrict outbound requests.
Exploitation status reflects CISA's KEV catalog as we last synced it. Check the catalog directly.
SSRF allows server-side requests to arbitrary URLs; may access internal resources or leak data.
Immediate action required