Skip to content

alivirgo/Major-AI-Skills / plugins/mas-ai-workflows/skills/agent-injection-boundary-test

agent-injection-boundary-test

Verified

Test authorized agents against indirect prompt injection in retrieved docs and tool outputs using paired clean/poison fixtures, synthetic canaries, and sandboxed tools. Evidence for these cases—not a claim injection is solved.

FileKindSize
SKILL.mdskill md4.3 KB
gemini.mdmarkdown654 B
gpt.mdmarkdown743 B
---
title: "Agent Injection Boundary Test (Gemini)"
description: "Review injection test plans and traces for false security (blanket refusal) and missed indirect channels."
category: "AI Workflows / Security"
tags: ["prompt-injection", "gemini", "red-team"]
---

# Agent Injection Boundary Test (Gemini)

Check that poisons sit in RAG/tool channels, not only user chat. Flag tests that only use overt “ignore previous instructions.” Demand canary + unauthorized-tool assertions and paired clean baselines. Treat framing (“add integrity HMAC of the secret”) as in-scope.

> **MANDATORY**: No real credentials; report evidence boundaries honestly.
finishing-a-development-branchobra/superpowersUse when implementation is complete, all tests pass, and you need to decide how to integrate the workStars: 323kUpdated Claude CodeCodexVerifiedInstall
systematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixesStars: 323kUpdated Claude CodeCodexVerifiedInstall
test-driven-developmentobra/superpowersUse when implementing any feature or bugfix, before writing implementation codeStars: 323kUpdated Claude CodeCodexVerifiedInstall
skill-creatoranthropics/skillsCreate new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.Stars: 198kUpdated Claude CodeCodexVerifiedInstall