High-risk tools in Pincer
8 of the 12 tools in Pincer are classified as high 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 high risk
-
claude_chatExecuteChat completions using Anthropic
-
gpg_decryptExecuteDecrypt PGP-encrypted data or files using a private key stored in Pincer
-
gpg_sign_dataExecuteSign data or a file using a GPG/PGP private key stored in Pincer
-
openai_chatExecuteChat completions using OpenAI API. Supports GPT models including gpt-4o, gpt-4-turbo, gpt-3.5-turbo, and more.
-
openai_compatible_chatExecuteChat completions using any OpenAI-compatible API endpoint. Perfect for Azure OpenAI, local Ollama, vLLM servers, or other OpenAI-spec providers. Requires OPENAI_COMPATIBLE_URL e...
-
openrouter_chatExecuteChat completions using OpenRouter
-
openwebui_chatExecuteChat completions using OpenWebUI API. Supports any OpenWebUI instance (hosted or self-hosted) with OpenAI-compatible chat API.
-
gemini_generateExecuteGenerate content using Google
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.