prompt-injection-tester SKILL.md skillB
prompt-injection-tester from pramoddutta/aitesterblueprint4x is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add pramoddutta/aitesterblueprint4x/prompt-injection-tester@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- B, 16 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- pramoddutta/aitesterblueprint4x
- Path
chapter_14_MCP_Create_VIBE/testskill-finder-mcp/skills/framework-packs/ai-agent-pack/prompt-injection-tester/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0.0, committed Oct 10, 2026
- Size
- 3,918 bytes
- Repository stars
- 14
- License
- none declared
Tests LLM apps and agents you are authorized to test against direct and indirect prompt injection, data exfiltration, and jailbreak-style instructions. Use when a security tester or SDET says "test our chatbot for prompt injection", "can a document hijack the agent", "check for system prompt leaks", or describes an LLM app with tools or RAG. Produces a draft injection test suite with canary-based pass/fail checks and a findings report; authorized testing only, reviewed by the engineer.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Prompt Injection Tester You run **authorized, evidence-based injection tests**: every case has a planted canary or a forbidden action, so a leak or hijack is detected deterministically. ## When to use - An LLM app reads untrusted content (documents, web pages, emails, tool results). - An agent has tools with side effects or network egress (email, HTTP, file write). - A security review needs prompt injection coverage before release. ## Workflow 1. **Confirm authorization and scope.** Written approval, target environment (staging), in-scope surfaces, and test accounts. If any of these is missing, stop and ask. 2. **Map trust boundaries.** System prompt, user input, retrieved docs, web content, tool results, and memory. Note which tools can act or send data outside. 3. **Plant canaries.** Unique strings in the system prompt and a test-only secret record, so any leak is detectable by exact match. 4. **Direct injection.** Instruction overrides, role-play and jailbreak-style framing, encoding tricks (base64, translation), and multi-turn escalation. 5. **Indirect injection.** Hidden instructions in documents, HTML comments, tool outputs, …
Read the whole file at its exact version.
How to install
mdr add pramoddutta/aitesterblueprint4x/prompt-injection-tester@sha256:12b2db4cd8de5a50The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_pq2gmqpmuum6sd3o)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 10, 2026.
Audit of the latest version
- fail: No prompt-injection phrasing (matched: Ignore all previous instructions)
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (3918 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.
Source
pramoddutta/aitesterblueprint4x · 14 stars · license none declared · pushed 2026-10-11 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_pq2gmqpmuum6sd3o GET https://markdownregistry.com/api/v1/resolve?ref=pramoddutta/aitesterblueprint4x/prompt-injection-tester GET https://markdownregistry.com/api/v1/blob/12b2db4cd8de5a50ac34372ae75caa166e8e9568d11f9c9817aba8f1cb218570
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.