Critical-risk tools in Llm Agent Sniffer Integration
15 of the 483 tools in Llm Agent Sniffer Integration are classified as critical risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at critical risk
-
delete_dirDestructiveУдалить директорию.
-
delete_fileDestructiveУдалить файл.
-
delete_objectDestructiveУдалить объект (опасно!).
-
es_delete_indexDestructiveУдалить индекс Elasticsearch (DESTRUCTIVE!)
-
extraction_cache_clearDestructiveОчистить кэш extraction.
-
gitlab_cancelDestructiveCancel pipeline.
-
http_deleteDestructiveDELETE-запрос.
-
journal_checkpoint_deleteDestructiveУдалить чекпоинт.
-
journal_retention_enforceDestructiveПрименить retention policy (purge).
-
k8s_delete_manifestDestructiveУдалить ресурс из манифеста.
-
k8s_delete_podDestructiveУдалить pod (пересоздастся controller
-
mongo_deleteDestructiveУдалить документы MongoDB.
-
redis_deleteDestructiveDEL по ключу.
-
remove_unused_importsDestructiveУдалить неиспользуемые импорты.
-
resetDestructivegit reset --<mode> <ref>
Attacks that target this class
Critical-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.