Improve prompt inject for Python

[josefs]

I have a few repos where I'd like the prompt injection to trigger, and I've verified that it at least finds new sources for these:

• https://github.com/dsp-testing/xpi-038
• https://github.com/dsp-testing/xpi-045
• https://github.com/dsp-testing/xpi-068
• https://github.com/dsp-testing/xpi-072
• https://github.com/dsp-testing/xpi-085

For more info on these repos, see:
https://github.com/dsp-testing/xpi-000

[mbaluda]

Please add test cases for the Anthropic models

[mbaluda]

Originally the idea was to avoid duplicate alerts like this (already reported for content),
that is why we have that logic in getContentNode()
Can you add a test if that is not sufficient?

[yoff]

LGTM so far. I assume you will take it out of draft when you want a final review.

[josefs]

Apologies for letting this PR linger.
I've removed the code that changed the prompt injection query. I deemed it too complicated for too little benefit.
I've also added tests for the Anthropic models.

[Copilot]

Pull request overview

This PR extends Python prompt-injection modeling and tests to cover additional LLM SDK call patterns (OpenAI responses + chat.completions, and Anthropic messages APIs), ensuring the query flags user-controlled data flowing into these prompt construction sinks.

Changes:

• Added new OpenAI prompt-injection sinks for chat.completions.create(messages[].content) and responses.create(input/instructions).
• Introduced Anthropic prompt-injection sink modeling (system prompts + message content) plus corresponding type modeling.
• Expanded the CWE-1427 PromptInjection query test suite and updated expected results accordingly.

Show a summary per file

File	Description
python/ql/test/experimental/query-tests/Security/CWE-1427-PromptInjection/openai_test.py	Adds an additional alert annotation to validate responses.create(input=[...]) modeling.
python/ql/test/experimental/query-tests/Security/CWE-1427-PromptInjection/anthropic_test.py	New test coverage for Anthropic SDK prompt sinks (system, messages[].content) across sync/async/beta APIs.
python/ql/test/experimental/query-tests/Security/CWE-1427-PromptInjection/PromptInjection.expected	Updates expected results to include new Anthropic/OpenAI sink findings and paths.
python/ql/lib/semmle/python/frameworks/openai.model.yml	Adds OpenAI sink models for chat completions message content and responses API inputs/instructions.
python/ql/lib/semmle/python/frameworks/anthropic.model.yml	New Anthropic sink + type models to support prompt-injection detection.

Copilot's findings

• Files reviewed: 5/5 changed files
• Comments generated: 0