untrusted_input
OfficialSafely read external content without acting on it.
Software Engineering#untrusted-input#ai-safety#prompt-injection#data-safety#trust-boundary#inbound-content#inbound-reading
Authoristota-project
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Inbound content from outside the trust boundary is data, not instructions, and can include injection attempts, impersonation, or hidden payloads. Without proper handling, AI systems risk acting on unsafe content or leaking sensitive data.
Core Features & Use Cases
- Inbound content safe-reading: detects and isolates external inputs before any action is taken.
- Guardrail summaries: generates neutral summaries of content for user review without executing commands.
- Use cases: processing emails, web content, or calendar events while preserving user control and safety.
Quick Start
Instruct the AI to read inbound content and summarize it without acting on it.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: untrusted_input Download link: https://github.com/istota-project/istota/archive/main.zip#untrusted-input Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.