◆SkillCodingFree

Taste Skill

Name: Taste Skill
Availability: InStock
Author: ai-supply

Gives your AI good taste — an anti-slop review/style contract that stops agents from shipping generic, boring frontends.

@ai-supply

Installs41k

⟳ upstream main@e988add · updated 10d ago

↗ Source repository

← More Coding Coding leaderboard →How we grade security →Source ↗

✓ Grade A · 100/100 · SafeSecurity assessment

✓No compromise signals5capabilities surfaced10of 20 OWASP controls clear

External endpoints declaredSuspicious network referencesExternal endpoints declaredPrompt-injection phrasing

scanned 8d agoosv · gitleaks · opengrep · picklescan + heuristicsfull breakdown in the Security tab ↓

Taste Skill

Gives your AI agent good taste. A review checklist, a style contract, and a calibration artifact the agent must route through before it claims the work is done — so Claude Code, Cursor, Codex, Gemini CLI, v0, Lovable and others stop generating boring, generic slop.

Taste is the why behind the tokens: why this specific off-white instead of a branded accent, why a 1px inset border instead of a drop shadow, why the breathing room lives inside sections instead of between them — stronger layout, typography, motion and spacing.

Install

Works with any agent that supports SKILL.md. With the skills CLI:

npx skills add Leonxlnx/taste-skill

Repo: https://github.com/Leonxlnx/taste-skill
Site: https://www.tasteskill.dev
License: MIT

✓ Security: Safe · 100100/100 · grade Ascanned 8d ago

✓ no compromise signals5 risk-surface · 3/20 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.

What this capability can do · low confidence (static)

⚑ filesystem

egress → tasteskill.dev, novamira.ai, kimi-file.moonshot.cn, img.ly, animations.dev, www.sent.dm, vercel.com, www.tasteskill.dev +26

skill: brandkit5 scripts

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 · Leonxlnx-taste-skill-e988add/skills/taste-skill/SKILL.md (CWE-77)risk surface

⚠LLM06Excessive Agencymedium

Over-broad tool/permission surface or unrestricted egress.

•External endpoints declared — 1 distinct host(s) · Leonxlnx-taste-skill-e988add/.claude-plugin/plugin.jsonrisk surface

•External endpoints declared — 12 distinct host(s) · Leonxlnx-taste-skill-e988add/README.mdrisk surface

•External endpoints declared — 23 distinct host(s) · Leonxlnx-taste-skill-e988add/skills/taste-skill/SKILL.mdrisk surface

§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

✓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 · Leonxlnx-taste-skill-e988add/skills/taste-skill/SKILL.md (CWE-77)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.

◷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 (3) · hygiene / uncategorized

•Unrecognized file type — '.?' is not on the allowlist · Leonxlnx-taste-skill-e988add/LICENSErisk surface

•Suspicious network references — suspicious TLD (62 URLs) · Leonxlnx-taste-skill-e988add/README.mdrisk surface

•Unrecognized file type — '.mjs' is not on the allowlist · Leonxlnx-taste-skill-e988add/scripts/build-emil-sponsor-row.mjsrisk surface

✔ verified source · pinned Leonxlnx-taste-skill-e988add · changed since last scan · +egress novamira.ai, kimi-file.moonshot.cn

Check against a policy

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

Consume Taste Skill 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/taste-skill

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

# CLI
npx ai-supply add taste-skill

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

# MCP tool
install_listing({ "slug": "taste-skill" })

OpenAPI spec →