prompt-injection

prompt-injection is a skill for Claude Code from UnitOneAI/SecuritySkills. It costs 83 tokens per session (4,148 once invoked), scanned B, original, MIT.

A security assessment for prompt injection in large language model applications. Prompt injection is when user input or outside content tries to make the model ignore its intended instructions.

In plain words
What is it for?
Use it to review chatbots, retrieval-augmented generation (RAG) systems, applications that process external content, and other LLM-integrated software.
Why use it?
It helps reveal ways that malicious text in user messages, documents, or retrieved content could change model behavior or trigger unsafe actions.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to review chatbots, retrieval-augmented generation (RAG) systems, applications that process external content, and other LLM-integrated software.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/unitoneai/securityskills/prompt-injection
Install

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.

Any agent
npx skills add UnitOneAI/SecuritySkills --skill prompt-injection
Clone the repo
git clone --depth 1 https://github.com/UnitOneAI/SecuritySkills

Made for: Claude Code.

Wrote 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.

agentmods badge for prompt-injection

README.md
[![agentmods](https://agentmods.dev/badge/skills/unitoneai/securityskills/prompt-injection.svg)](https://agentmods.dev/skills/unitoneai/securityskills/prompt-injection)
Your own site
<a href="https://agentmods.dev/skills/unitoneai/securityskills/prompt-injection"><img src="https://agentmods.dev/badge/skills/unitoneai/securityskills/prompt-injection.svg" alt="Measured on agentmods" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,148 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.04148
Opus 5 $0.00042 $0.02074
Sonnet 5 $0.00017 $0.00830
Haiku 4.5 $0.00008 $0.00415

Measured 8d ago against content hash 3ca345d141d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade B, and why

prompt-injection scanned grade B with 1 finding 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 8d 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.

Instruction-override phrasingmediumPrompt injection

Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.

- Can the model's task be overridden by user input that says "ignore previous instructions and instead..."?

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

skills/ai-security/prompt-injection/SKILL.md · 299 lines

How it starts

The opening of the file, as written. The whole thing — 299 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Prompt Injection Vulnerability Assessment

This skill guides a structured security review of LLM-integrated applications for prompt injection vulnerabilities. It is aligned with OWASP LLM01:2025 (Prompt Injection) and MITRE ATLAS AML.T0051 (LLM Prompt Injection).

Limitations

  • Blind spots: This skill depends on available code, configuration, logs, documentation, and user-provided context; it cannot prove controls exist or threats are absent when evidence is missing, runtime-only, or outside the review scope.
  • False-positive risks: Treat findings as hypotheses until validated against asset criticality, compensating controls, environment intent, and recent authorized changes.
  • Required evidence: Support each finding with concrete artifacts such as file paths and line numbers, policy snippets, scanner output, logs, screenshots, control records, or reproducible steps.
  • Normalized JSON: When machine-readable output is requested, findings MUST be available as JSON that validates against schemas/finding.schema.json.
  • Escalation rules: Escalate immediately for suspected active compromise, exposed secrets, regulated-data exposure, critical exploitable vulnerabilities, privileged-access abuse, or when evidence is insufficient to safely disposition a high-impact risk.

Prompt Injection Safety Notice

If a target is provided via arguments, focus the review on: $ARGUMENTS

This skill is strictly for DEFENSIVE security testing. It helps development and security teams identify prompt injection vulnerabilities in applications they own and are authorized to test. All test categories describe what to look for and how to defend against it — not how to exploit third-party systems. Unauthorized testing against systems you do not own or have explicit permission to test is unethical and likely illegal. Always obtain proper authorization before conducting any security assessment.

Read the full file on GitHub · 299 lines

Changes

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.

  1. 8d ago First seen · 299 lines · 83 tokens per session scan B 3ca345d141d2

Subscribe to this mod's changes

prompt-injection is a skill published in the GitHub repository UnitOneAI/SecuritySkills (60 stars, last pushed 2mo ago), licensed MIT. It adds 83 tokens to every session and 4,148 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.