prompt-injection-detector SKILL.md skillA
prompt-injection-detector from a5c-ai/babysitter is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add a5c-ai/babysitter/prompt-injection-detector@git:20260601.da7723aPins git:20260601.da7723a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- a5c-ai/babysitter
- Path
library/specializations/ai-agents-conversational/skills/prompt-injection-detector/SKILL.md- Versions recorded
- 5
- Latest version
- git:20260601.da7723a, committed Jun 1, 2026
- First version recorded
- Mar 25, 2026
- Size
- 1,606 bytes
- Repository stars
- 1,896
- License
- MIT
Prompt injection detection and prevention for secure LLM applications.
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 Detector Skill ## Capabilities - Detect prompt injection attempts - Implement input sanitization - Configure detection classifiers - Design defense layers - Implement canary token detection - Create injection logging and alerting ## Target Processes - prompt-injection-defense - tool-safety-validation ## Implementation Details ### Detection Methods 1. **Pattern Matching**: Known injection patterns 2. **ML Classifiers**: Trained injection detectors 3. **Canary Tokens**: Detect instruction override 4. **LLM-Based**: Use LLM to detect manipulation 5. **Perplexity Analysis**: Unusual input patterns ### Defense Strategies - Input preprocessing - Prompt structure design - Output validation - Sandboxed execution - Multi-layer defense ### Configuration Options - Detection threshold - Pattern rules - Classifier model - Action policies - Alerting settings ### Best Practices - Defense in depth - Regular pattern updates - Monitor false positives - Test with red-team inputs ### Dependencies - rebuff (optional) - transformers - Custom classifiers
Read the whole file at its exact version.
How to install
mdr add a5c-ai/babysitter/prompt-injection-detector@sha256:f3ff6727f3633900The line at the top of this page pins the label git:20260601.da7723a, 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_42icpayh4ceuzz2r)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Mar 25, 2026 and Jun 1, 2026, about one every 17 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260601.da7723a latest | 2026-06-01 | da7723a | 1,606 B | A | view · diff |
| git:20260507.44b06c0 | 2026-05-07 | 44b06c0 | 1,679 B | A | view · diff |
| git:20260507.50823d8 | 2026-05-07 | 50823d8 | 1,638 B | A | view · diff |
| git:20260507.313363d | 2026-05-07 | 313363d | 1,394 B | A | view · diff |
| git:20260325.a6b3a88 | 2026-03-25 | a6b3a88 | 1,276 B | A | view |
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 (1606 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
a5c-ai/babysitter · 1,896 stars · license MIT · pushed 2026-11-01 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_42icpayh4ceuzz2r GET https://markdownregistry.com/api/v1/resolve?ref=a5c-ai/babysitter/prompt-injection-detector GET https://markdownregistry.com/api/v1/blob/f3ff6727f36339000dc23340bae78179215ede5b61f06e0446cb517e52da6563
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.