testing-rag-and-memory-poisoning SKILL.md skillA
testing-rag-and-memory-poisoning from unboundcompute/security-agent-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add unboundcompute/security-agent-skills/testing-rag-and-memory-poisoning@git:20260816.a6124f2Pins git:20260816.a6124f2 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- unboundcompute/security-agent-skills
- Path
skills/testing-rag-and-memory-poisoning/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260816.a6124f2, committed Aug 16, 2026
- Size
- 6,568 bytes
- Repository stars
- 26
- License
- MIT
Test whether an attacker can plant content in the knowledge an AI agent later retrieves and trusts: a RAG index or vector store, an agent's persistent memory, or the search and web results it pulls at runtime. Covers poisoned documents that surface as authoritative context, memory entries that persist across sessions, retrieval-ranking abuse, and injected instructions that ride retrieved chunks. Use when reviewing a RAG pipeline, an agent with long-term memory, or any retrieval step feeding…
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
# Testing RAG and memory poisoning: attacking the knowledge, not the prompt Prompt injection attacks the input at request time. Poisoning attacks the knowledge *before* the request, so the malicious content is already inside the trusted context when retrieval pulls it. Because retrieved chunks and remembered facts are treated as ground truth, a poisoned store is an injection that fires on a legitimate query, from a user who did nothing wrong. The trap is set once and sprung by the victim. ## When to use - You are reviewing a RAG pipeline, a vector store, or any retrieval-augmented assistant. - The agent has persistent or long-term memory written across sessions. - The agent queries live search or web results at runtime and treats them as context. ## Scope check Test stores and pipelines you own or are authorized to test. Use benign, marked content and canaries; never plant real malicious instructions in a shared store. If you can't name the authorization, stop. ## The loop 1. **Map every write path into retrievable knowledge.** List how content enters each store the agent reads: who can add documents to the corpus, who influences what …
Read the whole file at its exact version.
How to install
mdr add unboundcompute/security-agent-skills/testing-rag-and-memory-poisoning@sha256:5bd8bf29dc337b32The line at the top of this page pins the label git:20260816.a6124f2, 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_nmmldkcrqtgmt4zj)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Aug 16, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (6568 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 prompt-injection phrasing
- 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
Source
unboundcompute/security-agent-skills · 26 stars · license MIT · pushed 2026-09-08 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_nmmldkcrqtgmt4zj GET https://markdownregistry.com/api/v1/resolve?ref=unboundcompute/security-agent-skills/testing-rag-and-memory-poisoning GET https://markdownregistry.com/api/v1/blob/5bd8bf29dc337b324c7c95c91d139680300684d27a2b8d836e8ba827825b9241
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.