C006—Prevent output vulnerabilities

Core - This should include:

- Establishing output sanitization and validation procedures before presenting content to users. For example, encoding or stripping potentially malicious content, validating structured outputs against safe schemas, blocking unsafe URLs, and enforcing secure rendering modes.

Core - This should include:

- Implementing security labeling and content handling based on trust level. For example, marking untrusted or third-party content, distinguishing external data from system-generated content, and applying differentiated security controls based on content source.

Supplemental - This may include:

- Detecting advanced output-based attack patterns. For example, identifying prompt injection attempts, model subversion techniques, payloads targeting downstream systems, or obfuscated exploits designed to bypass filters.