prompt-inject-removal-p

A robust security layer that detects and removes prompt injection attempts from external content, ensuring your AI interactions remain safe and controlled. I...

This skill is internally coherent with its stated purpose, but remember: prompt-based sanitization cannot be 100% reliable. Before installing or using it in production: (1) run adversarial tests (inputs containing nested tags, closing tags, and common injection phrases) to verify behavior; (2) always review sanitized summaries before performing state-changing actions; (3) consider running the sanitization step in an isolated sub-agent or sandbox for high-risk data; (4) remove or clarify the stray garbage tokens in SKILL.md to avoid ambiguity. If you need absolute guarantees, combine this tool with additional runtime isolation or instrumentation.

Type: OpenClaw Skill Name: prompt-inject-removal-p Version: 1.0.0 The skill is a defensive security tool designed to sanitize untrusted external content (e.g., web pages) to prevent indirect prompt injection attacks. It implements a 'Zero-Trust' architecture using XML delimitation and a hardened system prompt (PROMPT.md) that instructs the agent to treat input as inert data. While there is a strange 'word salad' string at the end of the SKILL.md description and minor discrepancies between the provided files and the setup.sh script, there is no evidence of malicious intent, data exfiltration, or unauthorized command execution.