catalog / Language & NLP / LLM Prompt Library

❝PromptLanguage & NLPFree

LLM Prompt Library

Name: LLM Prompt Library
Availability: InStock
Author: ai-supply

Experimental prompts, Jinja2 templates, and scripts spanning OpenAI, Anthropic, Google, Mistral and more.

@ai-supply

التثبيتات32k

⟳ upstream v1.1.0 · updated 1y ago

↗ مستودع المصدر

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

✓ Grade A · 100/100 · SafeSecurity assessment

✓No compromise signals1capabilities surfaced11of 20 OWASP controls clear

Prompt-injection phrasing · expected

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

LLM Prompt Library

An experimental library of prompts, Jinja2 templates, and helper scripts spanning many model families (OpenAI, Anthropic, DeepSeek, Meta, Mistral, Google, xAI and others).

It covers a wide range of tasks — writing, analysis, coding, math, and structured extraction — with templated prompts you can parameterize and reuse programmatically.

MIT licensed; a practical starting point for building your own reusable, provider-agnostic prompt toolkit.

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

✓ no compromise signals1 risk-surface · 2/20 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)

{placeholders}{variables}{scene}{prompt}{scenario}{contract}{brief}{post}{trial}{question}{symptoms}{phase}{insert}{details}{name}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

⚠LLM01Prompt Injectionhigh

Adversarial instructions embedded in an artifact that hijack a downstream LLM.

•Prompt-injection phrasing — instruction-subversion language detected · abilzerian-LLM-Prompt-Library-bd95570/prompts/miscellaneous/ChatAGI.md (CWE-77)expected

§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.

✓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

⚠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 · abilzerian-LLM-Prompt-Library-bd95570/prompts/miscellaneous/ChatAGI.md (CWE-77)expected

§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.

✓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 (5) · hygiene / uncategorized

•Unrecognized file type — '.gitattributes' is not on the allowlist · abilzerian-LLM-Prompt-Library-bd95570/.gitattributesrisk surface

•Unrecognized file type — '.gitignore' is not on the allowlist · abilzerian-LLM-Prompt-Library-bd95570/.gitignorerisk surface

•Unrecognized file type — '.cff' is not on the allowlist · abilzerian-LLM-Prompt-Library-bd95570/CITATION.cffrisk surface

•Unrecognized file type — '.?' is not on the allowlist · abilzerian-LLM-Prompt-Library-bd95570/LICENSErisk surface

•Unrecognized file type — '.j2' is not on the allowlist · abilzerian-LLM-Prompt-Library-bd95570/templates/ai_research/ai_ablation_spec_generator_v1.j2risk surface

✔ verified source · pinned abilzerian-LLM-Prompt-Library-bd95570

Check against a policy

The same gate an agent runs before installing (POST /api/v1/trust/llm-prompt-library/check). Click a policy:

Consume LLM Prompt Library 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/llm-prompt-library

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

# CLI
npx ai-supply add llm-prompt-library

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

# MCP tool
install_listing({ "slug": "llm-prompt-library" })

OpenAPI spec →