christop ea47f3097e fix(web_fetch): add SSRF guard for model-supplied URLs ...

web_fetch fetched any http/https URL a model emitted, checking only the
scheme. It performed requests.get(..., allow_redirects=True) with no
hostname resolution check and no private/loopback/link-local/cloud-metadata
filtering, and never re-validated redirect targets. A model (including one
under prompt injection) could make CowAgent fetch 127.0.0.1, RFC1918,
169.254.169.254 or other internal endpoints and return their bodies into
the conversation; a public URL could also 302-bounce into a private target.

The repo already shipped an SSRF validator for the vision tool
(Vision._validate_url_safe). Extract that logic into a shared helper
(agent/tools/utils/url_safety.py) and reuse it:

- execute() now validates the URL before dispatching to either fetch path.
- A new _safe_get() helper disables auto-redirect and follows redirects
  manually, re-validating every hop so a public URL cannot bounce into an
  internal address. Both the webpage and document fetch paths use it.
- Vision._validate_url_safe now delegates to the shared helper (public API
  unchanged), so both URL-consuming tools share one guard.

Stdlib only (ipaddress, socket, urllib.parse); no new dependency. Adds
tests/test_security_ssrf_web_fetch.py covering loopback, cloud-metadata,
RFC1918 and a public->loopback redirect.

Sink: agent/tools/web_fetch/web_fetch.py (_fetch_webpage / _fetch_document).
Signed-off-by: christop <825583681@qq.com>

2026-06-17 17:38:35 +08:00

19 KiB

Raw Blame History

View Raw