Unverified50% confidenceFactExact time
The newly added safety identifiers give image requests and responses a clearer ability to pass security context, enabling content safety policies to be embedded more tightly into the API call chain.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/17/2026
First Seen
Valid until: 1/15/2027
Sources
Related Entities
Related Claims
UnverifiedThe API now supports image URL input and provides more detailed security warning explanations.80% similarUnverifiedWrapping untrusted user-provided content in separate tags both prevents prompt injection attacks and helps the model maintain the correct role orientation69% similarUnverifiedThe Anthropic-compatible interface follows the Messages API specification, with the endpoint at /v1/messages; the system prompt is a top-level independent field, and in the response structure, content is an array of objects containing type and text.64% similarUnverifiedResponses added support for opt-in receipt of incremental WebSocket text and tool call snapshots.63% similarUnverifiedPublishing a post with an image via the LinkedIn API usually takes two steps: first upload the image through the registered upload endpoint and obtain the image asset URN, then call the create post endpoint to submit the author identity, text, and image asset URN combined.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1049995API
curl https://kongchang.com/api/v1/knowledge/claims/1049995MCP
get_claim(id=1049995)