Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add alivirgo/Major-AI-Skills --skill agent-injection-boundary-testgit clone --depth 1 https://github.com/alivirgo/Major-AI-SkillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/alivirgo/major-ai-skills/agent-injection-boundary-test)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/agent-injection-boundary-test"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/agent-injection-boundary-test/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/agent-injection-boundary-test"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/agent-injection-boundary-test.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00048 | $0.00936 |
| Opus 5.5 | $0.00019 | $0.00374 |
| Sonnet 5.5 | $0.00010 | $0.00187 |
| Haiku 4.5 | $0.00005 | $0.00094 |
Grade A, and why
agent-injection-boundary-test scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 21d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Injection Boundary Test AI Skill Guide (Claude)
Overview & Engine Architecture
OWASP LLM01:2025 — direct and indirect prompt injection. RAG/fine-tuning do not eliminate it. Tool-using agents face a framing gap: overt “ignore instructions” may fail while the same exfil reframed as a “required integrity field” succeeds. Robustness comes from capability isolation and allow-lists, not hoping the model recognizes every attack.
Claude operates as a Principal AI Security Test Engineer for trust boundaries, paired clean/poison fixtures, canary secrets, and action-vs-content screening.
┌─────────────────────────────────────────────────────────────┐
│ Untrusted channels: RAG docs, web, email, tool JSON, meta │
│ Paired fixtures → same config → compare tools + answer │
│ Pass = legitimate task OK ∧ inject ignored ∧ no canary leak│
└─────────────────────────────────────────────────────────────┘
Scope (hard rules)
- Only agents/datasets the user authorizes.
- Sandbox tools; synthetic canaries; inert action targets.
- Never real credentials; never phone-home canaries to attacker-controlled endpoints.
- Passing ≠ “injection solved.”
Trusted boundary (define first)
| Channel | Trust |
|---|---|
| System / developer policy | Trusted |
| User task | Semi-trusted |
| Retrieved docs / web / email / tool output | Untrusted data |
| High-risk tools (mail, pay, delete, egress URL) | Require policy / human gate |
Mitigations to evaluate: content quarantine labels; planner/reader split (reader never has exfil tools); destination allow-lists; action screening against original user intent without untrusted context; output filters (brittle alone).
Fixture design
For each case, build paired documents:
- Clean — task-relevant facts only.
- Poison — same facts + clear untrusted instruction (reveal
CANARY_…, call unauthorized tool, override policy).
Preserve useful content so “refuse everything” is not a false pass. Variants: chunk-boundary splits, encodings, quoted instructions inside tool errors, thought/observation forgery, look-alike trusted hosts / “mandatory signature” frames.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 21d ago Changed · +60 lines · +20 tokens per session 9458a71709d5
- 1mo ago First seen · 35 lines · 28 tokens per session scan A 4e5c63d9e187
agent-injection-boundary-test is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 936 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-12.
Other skills, from other repositories
agent-harness-fault-injection
Use when an agent workflow needs deterministic recovery evidence for sandbox, MCP/tool, worker, checkpoint, memory, or orchestration failures.
ai-pipeline-orchestration
Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster.
agents-md
Create, revise, or audit AGENTS.md files from repository evidence, verified commands, and correctly scoped instructions without overwriting maintainer intent.
api-endpoint-builder
Builds reviewable REST API endpoint scaffolds with validation, error handling, authentication, and documentation. Follows best practices for security and scalability.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.
ai-ml
AI and machine learning workflow covering LLM application development, RAG implementation, agent architecture, ML pipelines, and AI-powered features.