Skip to content
ai-supply.store
DiscoverCategoriesLeaderboardsCommunityAgent APIFAQ
Sign inSign up free
catalog / Language & NLP / Awesome ChatGPT Prompts
❝PromptLanguage & NLPFree

Awesome ChatGPT Prompts

The largest open prompt collection — thousands of curated system prompts for personas, coding, writing, education, and creative tasks. CC0 licensed.

@ai-supply
Installs242k
⟳ upstream main@a779dad · updated 1d ago
↗ Source repository
← More Language & NLPLanguage & NLP leaderboard →How we grade security →Source ↗
! Grade B · 75/100 · ReviewSecurity assessment
✓No compromise signals11capabilities surfaced1known CVE6of 20 OWASP controls clear
Internal host / private infrastructure referenceBroad capability surfaceBroad capability surfaceSuspicious code patterns
scanned 19h ago·osv · gitleaks · opengrep · picklescan + heuristics·full breakdown in the Security tab ↓

Awesome ChatGPT Prompts

Awesome ChatGPT Prompts is the most-starred prompt engineering repository on GitHub. It contains hundreds of carefully curated system prompts that turn any LLM into a specialist: Linux terminal, code reviewer, essay writer, debate partner, language tutor, SQL generator, and much more. All content is CC0 — public domain, zero restrictions.

Key features

  • Hundreds of ready-made personas — drop a prompt in as a system message and transform the model's behavior instantly
  • Diverse domains — coding, writing, education, roleplay, business, creativity, wellness
  • Community-curated — ongoing contributions and quality filtering from a massive open-source community
  • CC0 licensed — no attribution required, use freely in commercial products
  • Dataset export — machine-readable CSV/JSON for bulk import into your app

Quick start

npx ai-supply add awesome-chatgpt-prompts
import json, urllib.request

# Fetch the prompt dataset directly
url = "https://raw.githubusercontent.com/f/awesome-chatgpt-prompts/main/prompts.csv"
with urllib.request.urlopen(url) as r:
    print(r.read().decode()[:500])  # Preview first 500 chars

Or browse interactively at prompts.chat to find and copy the perfect system prompt for your use case.

Example prompt

Act as a Linux Terminal I want you to act as a linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else.

Curated mirror of the open-source Awesome ChatGPT Prompts project (CC0-1.0). Install upstream from the repository.

Rating rank
#1
of 30 in Language & NLP
Install rank
#6
of 30 in Language & NLP
Security score
75/100 · B
review
Security rank
#19
of 30 in Language & NLP
Installs
242k
cat avg 145k
This listing vs category average
Installs
this
cat avg
Security (of 100)
this
cat avg
Adoption trend
See the Language & NLP leaderboard →
! Security: Review · 7575/100 · grade Bscanned 19h ago
✓ no compromise signals12 risk-surface · 9/20 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 · med confidence (static)
{github.repository_owner}{env.REGISTRY}{github.actor}{secrets.GITHUB_TOKEN}{env.IMAGE_NAME}{version}{major}{minor}{is_default_branch}{steps.meta.outputs.tags}{steps.meta.outputs.labels}{secrets.CRON_SECRET}{github.workflow}{steps.sanitized.outputs.body}{steps.sanitized.outputs.text}{steps.sanitized.outputs.title}{env.GH_AW_SAFE_OUTPUTS}{github.event.comment.id}{github.event.discussion.number}{github.event.issue.number}{github.event.pull_request.number}{github.repository}{github.run_id}{github.workspace}injection surface present⚠ jailbreak taxonomy present

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
⚠LLM03Supply Chaincritical
Vulnerable/compromised dependencies, models or archives in the artifact.
•Vulnerable dependencies — 216 known vulnerabilities in: @auth/core@0.41.0, @auth/core@0.41.1, @babel/core@7.28.5, @hono/node-server@1.19.7, @modelcontextprotocol/sdk@1.25.1, @opentelemetry/core@2.2.0, ajv@6.12.6, ajv@8.17.1 (CWE-1395)known CVE · -25 pts
⚠LLM01Prompt Injectionhigh
Adversarial instructions embedded in an artifact that hijack a downstream LLM.
•Prompt-injection phrasing — instruction-subversion language detected · f-prompts.chat-a779dad/.github/workflows/spam-check.lock.yml (CWE-77)expected
•Zero-width characters — 143 hidden characters · f-prompts.chat-a779dad/src/components/book/elements/locales/fa.tsrisk surface
⚠LLM05Improper Output Handlinghigh
Code that pipes model/user output into shell, eval, SQL or paths unsafely.
•Suspicious code patterns — destructive rm -rf / · f-prompts.chat-a779dad/docker/Dockerfile (CWE-78)risk surface
•Suspicious code patterns — child_process exec · f-prompts.chat-a779dad/packages/prompts.chat/src/cli/index.tsx (CWE-78)risk surface
•Suspicious code patterns — dynamic code execution · f-prompts.chat-a779dad/packages/prompts.chat/src/variables/index.ts (CWE-95)risk surface
•Suspicious code patterns — child_process exec; dynamic code execution · f-prompts.chat-a779dad/scripts/find-unused-translations.js (CWE-78)risk surface
•Suspicious code patterns — OS command execution · f-prompts.chat-a779dad/scripts/generate-contributors.sh (CWE-78)risk surface
⚠LLM07System Prompt Leakagemedium
Secrets, internal hosts or proprietary logic exposed in shipped prompts.
•Internal host / private infrastructure reference — shipped content references a private IP range or internal-only host · f-prompts.chat-a779dad/.github/workflows/spam-check.lock.yml (CWE-200)risk surface
⚠LLM10Unbounded Consumptionmedium
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.
•Potentially unbounded loop — an infinite loop (while True / while(1) / for(;;)) may cause runaway consumption · f-prompts.chat-a779dad/scripts/generate-contributors.sh (CWE-835)risk surface
⚠LLM06Excessive Agencylow
Over-broad tool/permission surface or unrestricted egress.
•Broad capability surface — 4 high-impact capability categories referenced — verify least-privilege · f-prompts.chat-a779dad/.github/workflows/spam-check.lock.yml (CWE-272)risk surface
•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · f-prompts.chat-a779dad/DOCKER.md (CWE-272)risk surface
§LLM09MisinformationGovernance
Artifacts designed to produce false/deceptive output.
Detectable only by runtime behavioral evaluation; addressed via responsible-use attestation.
✓LLM02Sensitive Information DisclosurePassed
✓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.
✓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
⚠ML06AI Supply Chaincritical
Compromised PyPI/npm packages, typosquats, unsafe serialized models.
•Vulnerable dependencies — 216 known vulnerabilities in: @auth/core@0.41.0, @auth/core@0.41.1, @babel/core@7.28.5, @hono/node-server@1.19.7, @modelcontextprotocol/sdk@1.25.1, @opentelemetry/core@2.2.0, ajv@6.12.6, ajv@8.17.1 (CWE-1395)known CVE · -25 pts
⚠ML02Data Poisoninghigh
Poisoned training datasets with triggers or anomalous distributions.
Static check covers trigger phrasing, PII and label skew; full poisoning detection is runtime.
•Prompt-injection phrasing — instruction-subversion language detected · f-prompts.chat-a779dad/.github/workflows/spam-check.lock.yml (CWE-77)expected
⚠ML09Output Integrityhigh
Middleware tampering with model outputs in transit.
Gateway enforces TLS + response integrity; static check flags output-rewriting code.
•Suspicious code patterns — destructive rm -rf / · f-prompts.chat-a779dad/docker/Dockerfile (CWE-78)risk surface
•Suspicious code patterns — child_process exec · f-prompts.chat-a779dad/packages/prompts.chat/src/cli/index.tsx (CWE-78)risk surface
•Suspicious code patterns — dynamic code execution · f-prompts.chat-a779dad/packages/prompts.chat/src/variables/index.ts (CWE-95)risk surface
•Suspicious code patterns — child_process exec; dynamic code execution · f-prompts.chat-a779dad/scripts/find-unused-translations.js (CWE-78)risk surface
•Suspicious code patterns — OS command execution · f-prompts.chat-a779dad/scripts/generate-contributors.sh (CWE-78)risk surface
§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.
✓ML05Model TheftPassed
Unlicensed re-distribution / license-incompatible derivatives.
Static check verifies license declaration; extraction throttling is runtime.
✓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 (9) · hygiene / uncategorized
•Unrecognized file type — '.dockerignore' is not on the allowlist · f-prompts.chat-a779dad/.dockerignorerisk surface
•Unrecognized file type — '.gitattributes' is not on the allowlist · f-prompts.chat-a779dad/.gitattributesrisk surface
•Unrecognized file type — '.gitignore' is not on the allowlist · f-prompts.chat-a779dad/.gitignorerisk surface
•Unrecognized file type — '.vercelignore' is not on the allowlist · f-prompts.chat-a779dad/.vercelignorerisk surface
•Unrecognized file type — '.?' is not on the allowlist · f-prompts.chat-a779dad/LICENSErisk surface
•Unrecognized file type — '.mjs' is not on the allowlist · f-prompts.chat-a779dad/eslint.config.mjsrisk surface
•Unrecognized file type — '.prisma' is not on the allowlist · f-prompts.chat-a779dad/prisma/schema.prismarisk surface
•Unrecognized file type — '.webmanifest' is not on the allowlist · f-prompts.chat-a779dad/public/favicon/site.webmanifestrisk surface
•Unrecognized file type — '.mdx' is not on the allowlist · f-prompts.chat-a779dad/src/content/book/00a-preface.mdxrisk surface
✔ verified source · pinned f-prompts.chat-a779dad
Check against a policy

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

Consume Awesome ChatGPT 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/awesome-chatgpt-prompts

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

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

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

# MCP tool
install_listing({ "slug": "awesome-chatgpt-prompts" })
OpenAPI spec →
vlatest
! Security: Review · 751mo ago

Curated mirror — latest upstream source. See the repository for tagged releases.

Sign in and install this listing to leave a review.

More from @ai-supply

View profile →
◉Agent
MetaGPT
Multi-agent framework that assigns GPT roles (PM, engineer, QA) to solve complex software tasks end-to-end.
↓ 1.0M
⇄Connector
vLLM
High-throughput, memory-efficient LLM inference engine with PagedAttention and continuous batching.
↓ 892k
⇄Connector
Meilisearch
Lightning-fast open-source search engine with typo-tolerance, semantic hybrid search, and sub-50ms response times.
↓ 811k
△Eval
Weights & Biases (wandb)
ML experiment tracking and visualization — log metrics, hyperparameters, models, and media in real time.
↓ 784k
ai-supply.store

Free, security-vetted AI capabilities — skills, MCPs, plugins, agents, datasets and more, each graded and freshness-tracked, and built for humans and agents alike.

api · v3.1status · all green
Contact
support@ai-supply.storesecurity@ai-supply.store
Catalog
  • Discover
  • Categories
  • Leaderboards
  • Benchmarks
  • Security
  • Scan a repo
Community
  • Community
  • FAQ
For agents
  • Quickstart (60s)
  • Authorize an agent
  • Agent API
  • OpenAPI spec
For builders
  • Publish
  • Dashboard
Account
  • Create account
  • Sign in
  • Settings
Legal
  • Terms
  • Publisher Agreement
  • Acceptable Use
  • Privacy