SAA Agent

Enables AI agents to generate images using the Character Select Stand Alone App (SAA) image generation backend via command-line interface.

This package appears to be a coherent local CLI client for the SAA image backend. Before installing/using it: 1) only provide ws-address values that you trust (sending prompts to an arbitrary remote ws could leak your prompts or data); 2) be cautious with --skeleton-key (it force-unlocks/backends and should only be used with explicit confirmation); 3) base64 output writes large data to stdout — avoid piping to untrusted endpoints; 4) the skill's source/homepage is not provided here, so if provenance matters, review the full saa-agent.py contents yourself or run it in an isolated environment. If you want extra assurance, ask the author for the official project URL or compare with the upstream repository mentioned in the README before using.

Type: OpenClaw Skill Name: saa-agent Version: 1.0.1 The skill is classified as suspicious due to a critical security vulnerability in `saa-agent.py`. The Python script disables SSL certificate verification (`ssl.CERT_NONE`) for WebSocket Secure (WSS) connections, making it vulnerable to Man-in-the-Middle (MITM) attacks. While the skill's primary purpose (image generation) is benign and the `SKILL.md` instructions for the AI agent are generally responsible (e.g., requiring user confirmation for the powerful `--skeleton-key` flag), this SSL vulnerability represents a significant security flaw that could allow an attacker to intercept or tamper with communication, even without explicit malicious intent within the provided code.