python: Add query for prompt injection

This pull request introduces a new CodeQL query for detecting prompt injection vulnerabilities in Python code targeting AI prompting APIs such as agents and openai. The changes includes a new experimental query, new taint flow and type models, a customizable dataflow configuration, documentation, and comprehensive test coverage.

python/ql/lib/change-notes/2026-01-02-prompt-injection.md

@@ -0,0 +1,5 @@
+---
+category: minorAnalysis
+---
+* Added experimental query `py/prompt-injection` to detect potential prompt injection vulnerabilities in code using LLMs.
+* Added taint flow model and type model for `agents` and `openai` modules.

python/ql/lib/semmle/python/frameworks/agent.model.yml

@@ -0,0 +1,6 @@
+extensions:
+  - addsTo:
+      pack: codeql/python-all
+      extensible: sinkModel
+    data:
+      - ['agents', 'Member[Agent].Argument[instructions:]', 'prompt-injection']

python/ql/lib/semmle/python/frameworks/openai.model.yml

@@ -0,0 +1,12 @@
+extensions:
+  - addsTo:
+      pack: codeql/python-all
+      extensible: sinkModel
+    data:
+      - ['OpenAI', 'Member[beta].Member[assistants].Member[create].Argument[instructions:]', 'prompt-injection']
+
+  - addsTo:
+      pack: codeql/python-all
+      extensible: typeModel
+    data:
+      - ['OpenAI', 'openai', 'Member[OpenAI,AsyncOpenAI,AzureOpenAI].ReturnValue']