catalog / Language & NLP / ChatGPT System Prompts

❝PromptLanguage & NLPFree

ChatGPT System Prompts

Name: ChatGPT System Prompts
Availability: InStock
Author: ai-supply

Curated collection of high-quality system prompts for ChatGPT, organized by role and use case.

@ai-supply

Установки710

⟳ upstream main@e19d82a · updated 1y ago

↗ Исходный репозиторий

← More Language & NLP Language & NLP leaderboard →How we grade security →Source ↗

✓ Grade A · 100/100 · SafeSecurity assessment

✓No compromise signals13of 20 OWASP controls clear

scanned 1mo agoosv · gitleaks · opengrep · picklescan + heuristicsfull breakdown in the Security tab ↓

ChatGPT System Prompts

A curated collection of high-quality system prompts for ChatGPT and other conversational LLMs, organized by role and use case (teachers, developers, assistants, entertainers, and more).

Each entry is a ready-to-paste system message that steers the model into a specific persona or behavior, making it a handy reference for prompt engineers and anyone bootstrapping a new assistant.

Licensed MIT and dependency-free — it is plain markdown, so it is easy to browse, fork, and adapt into your own prompt library.

✓ Security: Safe · 100100/100 · grade Ascanned 1mo ago

✓ no compromise signals0 risk-surface · 0/20 OWASP controls flagged

Compromise signals — malicious or tampered code (leaked secrets, backdoors, a dropped executable) — reduce the score, and known dependency CVEs carry a bounded penalty (they warrant review but never QUARANTINE — update the dependency to clear). Other dangerous-by-capability traits are risk surface, expected for some capabilities. Every finding is mapped to its OWASP control below.

Prompt card · low confidence (static)

no template variables detected

Findings mapped to the OWASP Top 10 for LLM Applications (2025) and the OWASP Machine Learning Security Top 10. Expand any flagged control for the exact findings — compromise reduces the score; expected/risk-surface do not, except a known CVE, which carries a small bounded penalty (high/critical → Review).

OWASP Top 10 for LLM Applications

§LLM09MisinformationGovernance

Artifacts designed to produce false/deceptive output.

Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.

◷LLM10Unbounded ConsumptionRuntime-enforced

Unbounded loops/recursion causing DoS or runaway cost.

Enforced at runtime by the gateway (rate limits + spend caps + size caps); static check flags unbounded loops.

✓LLM01Prompt InjectionPassed

✓LLM02Sensitive Information DisclosurePassed

✓LLM03Supply ChainPassed

✓LLM04Data and Model PoisoningPassed

Backdoors/poisoning in training data or serialized models.

Behavioral poisoning needs model execution; static check covers unsafe serialization + dataset skew only.

✓LLM05Improper Output HandlingPassed

✓LLM06Excessive AgencyPassed

✓LLM07System Prompt LeakagePassed

✓LLM08Vector and Embedding WeaknessesPassed

PII or plaintext source leakage in embedding/vector exports.

Embedding inversion/poisoning is largely runtime; static check covers PII in vector exports.

OWASP Machine Learning Security Top 10

§ML01Input Manipulation (Adversarial)Governance

Models vulnerable to adversarial perturbations.

Requires runtime robustness evaluation; addressed via publisher robustness attestation.

§ML03Model InversionGovernance

Training data reconstructable from a model's outputs.

Runtime/evaluation property; addressed via model-card data-provenance + DP attestation.

§ML04Membership InferenceGovernance

Determining whether a record was in the training set.

Runtime/evaluation property; addressed via overfitting disclosure + DP attestation.

§ML08Model SkewingGovernance

Models trained on skewed data producing biased output.

Requires fairness evaluation; addressed via model-card bias/limitations disclosure.

◷ML09Output IntegrityRuntime-enforced

Middleware tampering with model outputs in transit.

Gateway enforces TLS + response integrity; static check flags output-rewriting code.

✓ML02Data PoisoningPassed

Poisoned training datasets with triggers or anomalous distributions.

Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.

✓ML05Model TheftPassed

Unlicensed re-distribution / license-incompatible derivatives.

Static check verifies license declaration; extraction throttling is runtime.

✓ML06AI Supply ChainPassed

✓ML07Transfer Learning AttackPassed

Backdoored base models / LoRA adapters propagating to derivatives.

Backdoor detection needs behavioral probing; static check covers unsafe serialization + provenance.

✓ML10Model Poisoning (Weights)Passed

Tampered model weight files; integrity must be verifiable.

Static check enforces safe formats + records a content hash for downstream verification.

Other findings (1) · hygiene / uncategorized

•Unrecognized file type — '.?' is not on the allowlist · mustvlad-ChatGPT-System-Prompts-e19d82a/LICENSErisk surface

✔ verified source · pinned mustvlad-ChatGPT-System-Prompts-e19d82a

Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/chatgpt-system-prompts/check). Click a policy:

Consume ChatGPT System Prompts programmatically. Authenticate with an API key or session — see Authorize an agent.

# Agents: CHECK BEFORE YOU INSTALL (no auth) — score, grade, level, capability manifest
curl https://ai-supply.store/api/v1/trust/chatgpt-system-prompts

# Gate against your org policy (returns { pass, violations })
curl -X POST https://ai-supply.store/api/v1/trust/chatgpt-system-prompts/check \
  -H "Content-Type: application/json" \
  -d '{"minGrade":"B","denyPermissions":["shell"],"denyUnknownEgress":true}'

# CLI
npx ai-supply add chatgpt-system-prompts

# REST (install → download)
curl -X POST https://ai-supply.store/api/v1/listings/chatgpt-system-prompts/install \
  -H "Authorization: Bearer $AIM_KEY"

# MCP tool
install_listing({ "slug": "chatgpt-system-prompts" })

OpenAPI spec →