From 93a26cb6c0f90cdfb33297784ecc581caae25d29 Mon Sep 17 00:00:00 2001 From: Sotiris Dragonas <36576941+BazookaMusic@users.noreply.github.com> Date: Fri, 19 Jun 2026 13:10:55 +0300 Subject: [PATCH] mark the ai-generated models with the correct provenance (they were manual because they were used as a baseline in the mads-llm project --- .../org.apache.avro.data.model.yml | 2 +- .../org.apache.avro.file.model.yml | 26 +++++------ .../llmgenerator/org.apache.avro.model.yml | 44 +++++++++---------- .../org.apache.avro.util.model.yml | 2 +- 4 files changed, 37 insertions(+), 37 deletions(-) diff --git a/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.data.model.yml b/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.data.model.yml index 98539e88ede..22ea4daa66d 100644 --- a/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.data.model.yml +++ b/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.data.model.yml @@ -5,7 +5,7 @@ extensions: pack: codeql/java-all extensible: summaryModel data: - - ["org.apache.avro.data", "Json$ObjectReader", True, "read", "(Object,Decoder)", "", "Argument[1]", "ReturnValue", "taint", "manual"] + - ["org.apache.avro.data", "Json$ObjectReader", True, "read", "(Object,Decoder)", "", "Argument[1]", "ReturnValue", "taint", "ai-generated"] - ["org.apache.avro.data", "Json$ObjectReader", True, "setSchema", "(Schema)", "", "Argument[0]", "Argument[this]", "taint", "df-generated"] - ["org.apache.avro.data", "TimeConversions$TimeMicrosConversion", True, "adjustAndSetValue", "(String,String)", "", "Argument[0]", "ReturnValue", "taint", "dfc-generated"] - ["org.apache.avro.data", "TimeConversions$TimeMicrosConversion", True, "adjustAndSetValue", "(String,String)", "", "Argument[1]", "ReturnValue", "taint", "dfc-generated"] diff --git a/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.file.model.yml b/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.file.model.yml index 842aa4afb52..9a5167002b2 100644 --- a/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.file.model.yml +++ b/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.file.model.yml @@ -5,22 +5,22 @@ extensions: pack: codeql/java-all extensible: sinkModel data: - - ["org.apache.avro.file", "DataFileReader", True, "DataFileReader", "(File,DatumReader)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro.file", "DataFileReader", True, "openReader", "(File,DatumReader)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro.file", "DataFileWriter", True, "appendTo", "(File)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro.file", "DataFileWriter", True, "create", "(Schema,File)", "", "Argument[1]", "path-injection", "manual"] - - ["org.apache.avro.file", "SeekableFileInput", True, "SeekableFileInput", "(File)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro.file", "SyncableFileOutputStream", True, "SyncableFileOutputStream", "(File)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro.file", "SyncableFileOutputStream", True, "SyncableFileOutputStream", "(File,boolean)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro.file", "SyncableFileOutputStream", True, "SyncableFileOutputStream", "(String)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro.file", "SyncableFileOutputStream", True, "SyncableFileOutputStream", "(String,boolean)", "", "Argument[0]", "path-injection", "manual"] + - ["org.apache.avro.file", "DataFileReader", True, "DataFileReader", "(File,DatumReader)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro.file", "DataFileReader", True, "openReader", "(File,DatumReader)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro.file", "DataFileWriter", True, "appendTo", "(File)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro.file", "DataFileWriter", True, "create", "(Schema,File)", "", "Argument[1]", "path-injection", "ai-generated"] + - ["org.apache.avro.file", "SeekableFileInput", True, "SeekableFileInput", "(File)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro.file", "SyncableFileOutputStream", True, "SyncableFileOutputStream", "(File)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro.file", "SyncableFileOutputStream", True, "SyncableFileOutputStream", "(File,boolean)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro.file", "SyncableFileOutputStream", True, "SyncableFileOutputStream", "(String)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro.file", "SyncableFileOutputStream", True, "SyncableFileOutputStream", "(String,boolean)", "", "Argument[0]", "path-injection", "ai-generated"] - addsTo: pack: codeql/java-all extensible: sourceModel data: - - ["org.apache.avro.file", "DataFileReader", True, "DataFileReader", "(File,DatumReader)", "", "Argument[this]", "file", "manual"] - - ["org.apache.avro.file", "DataFileReader", True, "openReader", "(File,DatumReader)", "", "ReturnValue", "file", "manual"] - - ["org.apache.avro.file", "SeekableFileInput", True, "SeekableFileInput", "(File)", "", "Argument[this]", "file", "manual"] + - ["org.apache.avro.file", "DataFileReader", True, "DataFileReader", "(File,DatumReader)", "", "Argument[this]", "file", "ai-generated"] + - ["org.apache.avro.file", "DataFileReader", True, "openReader", "(File,DatumReader)", "", "ReturnValue", "file", "ai-generated"] + - ["org.apache.avro.file", "SeekableFileInput", True, "SeekableFileInput", "(File)", "", "Argument[this]", "file", "ai-generated"] - addsTo: pack: codeql/java-all extensible: summaryModel @@ -30,7 +30,7 @@ extensions: - ["org.apache.avro.file", "DataFileReader", True, "DataFileReader", "(File,DatumReader)", "", "Argument[1]", "Argument[this]", "taint", "df-generated"] - ["org.apache.avro.file", "DataFileReader", True, "DataFileReader", "(SeekableInput,DatumReader)", "", "Argument[0]", "Argument[this]", "taint", "df-generated"] - ["org.apache.avro.file", "DataFileReader", True, "DataFileReader", "(SeekableInput,DatumReader)", "", "Argument[1]", "Argument[this]", "taint", "df-generated"] - - ["org.apache.avro.file", "DataFileReader", True, "openReader", "(File,DatumReader)", "", "Argument[0]", "ReturnValue", "taint", "manual"] + - ["org.apache.avro.file", "DataFileReader", True, "openReader", "(File,DatumReader)", "", "Argument[0]", "ReturnValue", "taint", "ai-generated"] - ["org.apache.avro.file", "DataFileReader", True, "openReader", "(File,DatumReader)", "", "Argument[1]", "ReturnValue", "taint", "df-generated"] - ["org.apache.avro.file", "DataFileReader", True, "openReader", "(SeekableInput,DatumReader)", "", "Argument[0]", "ReturnValue", "taint", "df-generated"] - ["org.apache.avro.file", "DataFileReader", True, "openReader", "(SeekableInput,DatumReader)", "", "Argument[1]", "ReturnValue", "taint", "df-generated"] diff --git a/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.model.yml b/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.model.yml index 279cd19c748..429e883e67c 100644 --- a/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.model.yml +++ b/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.model.yml @@ -5,29 +5,29 @@ extensions: pack: codeql/java-all extensible: sinkModel data: - - ["org.apache.avro", "Protocol", True, "parse", "(File)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro", "Schema", True, "parse", "(File)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro", "Schema$Parser", True, "parse", "(File)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro", "SchemaParser", True, "parse", "(File)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro", "SchemaParser", True, "parse", "(File,Charset)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro", "SchemaParser", True, "parse", "(Path)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro", "SchemaParser", True, "parse", "(Path,Charset)", "", "Argument[0]", "path-injection", "manual"] - - ["org.apache.avro", "SchemaParser", True, "parse", "(URI,Charset)", "", "Argument[0]", "request-forgery", "manual"] - - ["org.apache.avro", "SchemaParser", True, "parseSingle", "(Path)", "", "Argument[0]", "path-injection", "manual"] + - ["org.apache.avro", "Protocol", True, "parse", "(File)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro", "Schema", True, "parse", "(File)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro", "Schema$Parser", True, "parse", "(File)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro", "SchemaParser", True, "parse", "(File)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro", "SchemaParser", True, "parse", "(File,Charset)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro", "SchemaParser", True, "parse", "(Path)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro", "SchemaParser", True, "parse", "(Path,Charset)", "", "Argument[0]", "path-injection", "ai-generated"] + - ["org.apache.avro", "SchemaParser", True, "parse", "(URI,Charset)", "", "Argument[0]", "request-forgery", "ai-generated"] + - ["org.apache.avro", "SchemaParser", True, "parseSingle", "(Path)", "", "Argument[0]", "path-injection", "ai-generated"] - addsTo: pack: codeql/java-all extensible: sourceModel data: - - ["org.apache.avro", "Protocol", True, "main", "(String[])", "", "Parameter[0]", "commandargs", "manual"] - - ["org.apache.avro", "Protocol", True, "parse", "(File)", "", "ReturnValue", "file", "manual"] - - ["org.apache.avro", "Schema", True, "parse", "(File)", "", "ReturnValue", "file", "manual"] - - ["org.apache.avro", "Schema$Parser", True, "parse", "(File)", "", "ReturnValue", "file", "manual"] - - ["org.apache.avro", "SchemaParser", True, "parse", "(File)", "", "ReturnValue", "file", "manual"] - - ["org.apache.avro", "SchemaParser", True, "parse", "(File,Charset)", "", "ReturnValue", "file", "manual"] - - ["org.apache.avro", "SchemaParser", True, "parse", "(Path)", "", "ReturnValue", "file", "manual"] - - ["org.apache.avro", "SchemaParser", True, "parse", "(Path,Charset)", "", "ReturnValue", "file", "manual"] - - ["org.apache.avro", "SchemaParser", True, "parse", "(URI,Charset)", "", "ReturnValue", "remote", "manual"] - - ["org.apache.avro", "SchemaParser", True, "parseSingle", "(Path)", "", "ReturnValue", "file", "manual"] + - ["org.apache.avro", "Protocol", True, "main", "(String[])", "", "Parameter[0]", "commandargs", "ai-generated"] + - ["org.apache.avro", "Protocol", True, "parse", "(File)", "", "ReturnValue", "file", "ai-generated"] + - ["org.apache.avro", "Schema", True, "parse", "(File)", "", "ReturnValue", "file", "ai-generated"] + - ["org.apache.avro", "Schema$Parser", True, "parse", "(File)", "", "ReturnValue", "file", "ai-generated"] + - ["org.apache.avro", "SchemaParser", True, "parse", "(File)", "", "ReturnValue", "file", "ai-generated"] + - ["org.apache.avro", "SchemaParser", True, "parse", "(File,Charset)", "", "ReturnValue", "file", "ai-generated"] + - ["org.apache.avro", "SchemaParser", True, "parse", "(Path)", "", "ReturnValue", "file", "ai-generated"] + - ["org.apache.avro", "SchemaParser", True, "parse", "(Path,Charset)", "", "ReturnValue", "file", "ai-generated"] + - ["org.apache.avro", "SchemaParser", True, "parse", "(URI,Charset)", "", "ReturnValue", "remote", "ai-generated"] + - ["org.apache.avro", "SchemaParser", True, "parseSingle", "(Path)", "", "ReturnValue", "file", "ai-generated"] - addsTo: pack: codeql/java-all extensible: summaryModel @@ -404,8 +404,8 @@ extensions: - ["org.apache.avro", "SchemaParseException", True, "SchemaParseException", "(Throwable)", "", "Argument[0]", "Argument[this]", "taint", "df-generated"] - ["org.apache.avro", "SchemaParser", True, "SchemaParser", "(NameValidator)", "", "Argument[0]", "Argument[this]", "taint", "df-generated"] - ["org.apache.avro", "SchemaParser", True, "getParsedNamedSchemas", "()", "", "Argument[this]", "ReturnValue", "taint", "df-generated"] - - ["org.apache.avro", "SchemaParser$ParseResult", True, "mainSchema", "()", "", "Argument[this]", "ReturnValue", "taint", "manual"] - - ["org.apache.avro", "SchemaParser$ParseResult", True, "parsedNamedSchemas", "()", "", "Argument[this]", "ReturnValue", "taint", "manual"] + - ["org.apache.avro", "SchemaParser$ParseResult", True, "mainSchema", "()", "", "Argument[this]", "ReturnValue", "taint", "ai-generated"] + - ["org.apache.avro", "SchemaParser$ParseResult", True, "parsedNamedSchemas", "()", "", "Argument[this]", "ReturnValue", "taint", "ai-generated"] - ["org.apache.avro", "SchemaValidationException", True, "SchemaValidationException", "(Schema,Schema,Throwable)", "", "Argument[2]", "Argument[this]", "taint", "df-generated"] - ["org.apache.avro", "SchemaValidatorBuilder", False, "canBeReadStrategy", "()", "", "Argument[this]", "ReturnValue", "value", "dfc-generated"] - ["org.apache.avro", "SchemaValidatorBuilder", False, "canReadStrategy", "()", "", "Argument[this]", "ReturnValue", "value", "dfc-generated"] @@ -427,4 +427,4 @@ extensions: pack: codeql/java-all extensible: neutralModel data: - - ["org.apache.avro", "SchemaFormatterFactory", "getDefaultFormatter", "()", "summary", "manual"] + - ["org.apache.avro", "SchemaFormatterFactory", "getDefaultFormatter", "()", "summary", "ai-generated"] diff --git a/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.util.model.yml b/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.util.model.yml index 89e1b29db06..5365ffba070 100644 --- a/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.util.model.yml +++ b/java/ql/lib/ext/generated/llmgenerator/org.apache.avro.util.model.yml @@ -5,7 +5,7 @@ extensions: pack: codeql/java-all extensible: sourceModel data: - - ["org.apache.avro.util", "RandomData", True, "main", "(String[])", "", "Parameter[0]", "commandargs", "manual"] + - ["org.apache.avro.util", "RandomData", True, "main", "(String[])", "", "Parameter[0]", "commandargs", "ai-generated"] - addsTo: pack: codeql/java-all extensible: summaryModel