Python Sdk

Python SDK for inference.sh - run AI apps, build agents, and integrate with 150+ models. Package: inferencesh (pip install inferencesh). Supports sync/async,...

This skill appears to be a documentation-only SDK integration for inference.sh and is coherent with that purpose — but take the following precautions before using it: 1) The SDK requires an inference.sh API key (examples use INFERENCE_API_KEY) even though the skill metadata lists no required env vars; treat that key like any secret and limit its scope. 2) Examples show automatic upload of local file paths and large-file multipart uploads — avoid pointing the SDK at sensitive files unless you intend to send them to the external service. 3) Webhook tools and public=true file options can make data reachable to third parties; verify webhook URLs and permissions. 4) Several examples enable code execution and show use of eval — running untrusted expressions or auto-executing code from agents is dangerous; require human approval and sanitize inputs. 5) The skill bundle is instruction-only and has no provenance (homepage unknown, owner id only). Before installing or running pip install inferencesh, verify the package source (official website or PyPI project page) and review the actual pip package contents and version to ensure you’re installing the legitimate SDK. If you need higher assurance, ask the publisher for a homepage or source repository link and inspect the released package code.

Type: OpenClaw Skill Name: python-sdk Version: 0.1.5 This skill bundle is classified as suspicious due to the extremely broad permissions and powerful capabilities it exposes, which could be exploited via prompt injection against the AI agent. The `SKILL.md` explicitly grants `Bash(python *)` permission, allowing the agent to execute arbitrary Python code. Furthermore, the documentation details the use of `internal_tools().code_execution(True)` and `webhook_tool` (with `secret` access) for making external HTTP requests, which could be leveraged for data exfiltration or unauthorized actions if the agent is prompted maliciously. While the files themselves are documentation and do not contain explicit malware, the combination of broad execution permissions and powerful network/file access tools presents a significant attack surface.