@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / 7551a34032
Fork 0

A high-throughput and memory-efficient inference and serving engine for LLMs

Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git

Synced Nov 16, 02:00 UTC

[Docs] Document vulnerability disclosure process (#12326)

Signed-off-by: Russell Bryant <rbryant@redhat.com>

Russell Bryant committed Jan 22, 2025 at 22:44 UTC 7551a340328dec66d5905b01d0113e251c3afb3b
1 file changed +17
docs/source/contributing/vulnerability_management.md
+17
@@ -41,3 +41,20 @@ You may use the `#security` channel in the [VLLM Slack](https://slack.vllm.ai)
41 to discuss security-related topics. However, please do not disclose any
42 vulnerabilities in this channel. If you need to report a vulnerability, please
43 use the GitHub security advisory system or contact a VMT member privately.
44 +
45 +## Vulnerability Disclosure
46 +
47 +The process for disclosing vulnerabilities is the following:
48 +
49 +- The VMT will work with the project maintainers to develop a fix for the
50 + vulnerability.
51 +- The VMT will coordinate with the reporter and project maintainers to prepare a
52 + security advisory that adequately describes the vulnerability and its impact.
53 +- The VMT will coordinate with the project maintainers to publish a fix and
54 + release an update that includes that fix.
55 +- The VMT will publish the security advisory on GitHub. Release notes will be
56 + updated to include a reference to the security advisory.
57 +
58 +The VMT and project maintainers will work to minimize the amount of time in
59 +between disclosing any public information about the vulnerability and making a
60 +release and advisory available.