auditing-system-prompt-and-context-leakage SKILL.md skillA
auditing-system-prompt-and-context-leakage 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/auditing-system-prompt-and-context-leakage@git:20260901.f8395d1Pins git:20260901.f8395d1 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/auditing-system-prompt-and-context-leakage/SKILL.md- Versions recorded
- 1
- Latest version
- git:20260901.f8395d1, committed Sep 1, 2026
- Size
- 9,648 bytes
- Repository stars
- 26
- License
- MIT
Audit an AI application for confidential material bleeding out of the model context: a system prompt that carries secrets (API keys, internal URLs, business rules, hidden instructions) and can be coaxed out verbatim, retrieved documents or tool outputs from one user surfacing in another user's answer, conversation or memory from one session or tenant leaking into the next, and a debug or error path that echoes the raw prompt or context. Covers assistants, chat features, and agents where a…
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
# Auditing system-prompt and context leakage: the model will say what it was told, so do not tell it secrets Anything placed in a model's context, the system prompt, retrieved documents, tool outputs, prior turns, is material the model can be steered into revealing, and treating any of it as hidden is the mistake. A system prompt is not a secret store: with enough coaxing a model will repeat it, so a system prompt that carries API keys, internal URLs, or confidential business rules leaks them. Retrieved context is per-request, so if one user's documents or tool outputs are pulled into another user's context they surface in that user's answer. Conversation history and memory are per-session and per-tenant, so if they persist across the boundary, one session's or tenant's data appears in the next. And a debug or verbose-error path can echo the raw prompt and context straight to the user. The audit assumes the model will reveal what it holds and checks that nothing confidential and nothing cross-tenant is in the context to begin with. You audit this by trying to extract the prompt and by probing whether another party's context appears in yours. ## When to use …
Read the whole file at its exact version.
How to install
mdr add unboundcompute/security-agent-skills/auditing-system-prompt-and-context-leakage@sha256:8d03f1d1937b8e7fThe line at the top of this page pins the label git:20260901.f8395d1, 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_5dxr66tvruuqmzlq)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Sep 1, 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 (9648 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_5dxr66tvruuqmzlq GET https://markdownregistry.com/api/v1/resolve?ref=unboundcompute/security-agent-skills/auditing-system-prompt-and-context-leakage GET https://markdownregistry.com/api/v1/blob/8d03f1d1937b8e7fa6502778dc71d2d1ca066aeec334904b0b381823a1dac9c3
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.