6 Commits

Author	SHA1	Message	Date
Josef Svenningsson	25a8aa97b2	Fix openai prompt injection tests	2026-04-28 18:24:26 +01:00
Josef Svenningsson	a05e191518	Add tests for anthropic prompt injection models	2026-04-28 18:24:22 +01:00
Josef Svenningsson	e069c9c2ee	Fix tests	2026-04-28 18:24:19 +01:00
Owen Mansel-Chan	5a97348e78	python: Inline expectation should have space after $ ... This was a regex-find-replace from `# \$(?! )` (using a negative lookahead) to `# $ `.	2026-03-04 12:45:05 +00:00
Owen Mansel-Chan	3f08ff88a4	Pretty print models in test ... Otherwise the tests breaks when unrelated changes are made because the model numbers change	2026-02-04 10:52:44 +00:00
yoff	e7a0fc7140	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.	2026-01-29 23:47:52 +01:00