catalog / Language & NLP / Text Generator for Obsidian

⊕PluginLanguage & NLPFree

Text Generator for Obsidian

Name: Text Generator for Obsidian
Availability: InStock
Author: ai-supply

Obsidian plugin that generates note content via OpenAI, Anthropic, Google, and local models.

@ai-supply

インストール数27k

⟳ upstream 0.8.7 · updated 3mo ago

↗ ソースリポジトリ

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

✓ Grade A · 100/100 · SafeSecurity assessment

✓No compromise signals16capabilities surfaced7of 20 OWASP controls clear

External endpoints declaredBroad capability surfaceSuspicious network referencesExternal endpoints declared

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

Text Generator for Obsidian

A popular Obsidian plugin for generating text content inside your notes using a range of AI providers (OpenAI, Anthropic, Google, and local models).

It is built around reusable templates and context drawn from your vault, letting you draft, summarize, brainstorm, and expand notes without leaving Obsidian.

MIT licensed; a good fit for writers and researchers who want an AI writing assistant embedded in their knowledge base.

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

✓ no compromise signals16 risk-surface · 7/20 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)

egress → www.buymeacoffee.com, bit.ly, discord.gg, img.shields.io, twitter.com, img.youtube.com, www.youtube.com, contrib.rocks

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 Chainmedium

Vulnerable/compromised dependencies, models or archives in the artifact.

•Dependency manifest — 117 npm dependencies declared · nhaouari-obsidian-textgenerator-plugin-c83ecbd/package.jsonrisk surface

•Non-registry dependency source — 1 dependency/ies pulled from git/URL/file · nhaouari-obsidian-textgenerator-plugin-c83ecbd/package.json (CWE-829)risk surface

⚠LLM05Improper Output Handlingmedium

Code that pipes model/user output into shell, eval, SQL or paths unsafely.

•Suspicious code patterns — child_process exec; dynamic code execution · nhaouari-obsidian-textgenerator-plugin-c83ecbd/esbuild.config.mjs (CWE-78)risk surface

•Suspicious code patterns — child_process exec · nhaouari-obsidian-textgenerator-plugin-c83ecbd/scripts/remove-tag.js (CWE-78)risk surface

•Suspicious code patterns — dynamic code execution · nhaouari-obsidian-textgenerator-plugin-c83ecbd/src/helpers/javascript-sandbox.ts (CWE-95)risk surface

⚠LLM02Sensitive Information Disclosurelow

Secrets, credentials or PII shipped inside the artifact.

•Low-confidence secret match — 8 possible: generic-api-key · nhaouari-obsidian-textgenerator-plugin-c83ecbd/assets/tiktoken/encoders/cl100k_base.json (CWE-798)risk surface

•Low-confidence secret match — 2 possible: generic-api-key · nhaouari-obsidian-textgenerator-plugin-c83ecbd/assets/tiktoken/encoders/r50k_base.json (CWE-798)risk surface

•Low-confidence secret match — 2 possible: generic-api-key · nhaouari-obsidian-textgenerator-plugin-c83ecbd/assets/tiktoken/encoders/p50k_base.json (CWE-798)risk surface

⚠LLM06Excessive Agencylow

Over-broad tool/permission surface or unrestricted egress.

•External endpoints declared — 1 distinct host(s) · nhaouari-obsidian-textgenerator-plugin-c83ecbd/.github/FUNDING.ymlrisk surface

•Broad capability surface — 3 high-impact capability categories referenced — verify least-privilege · nhaouari-obsidian-textgenerator-plugin-c83ecbd/.github/workflows/release.yml (CWE-272)risk surface

•External endpoints declared — 8 distinct host(s) · nhaouari-obsidian-textgenerator-plugin-c83ecbd/README.mdrisk surface

•External endpoints declared — 2 distinct host(s) · nhaouari-obsidian-textgenerator-plugin-c83ecbd/manifest-beta.jsonrisk surface

•External endpoints declared — 4 distinct host(s) · nhaouari-obsidian-textgenerator-plugin-c83ecbd/src/LLMProviders/langchain/azureOpenAIChat.tsxrisk surface

•External endpoints declared — 3 distinct host(s) · nhaouari-obsidian-textgenerator-plugin-c83ecbd/src/LLMProviders/langchain/mistralaiChat.tsxrisk surface

⚠LLM07System Prompt Leakagelow

Secrets, internal hosts or proprietary logic exposed in shipped prompts.

•Low-confidence secret match — 8 possible: generic-api-key · nhaouari-obsidian-textgenerator-plugin-c83ecbd/assets/tiktoken/encoders/cl100k_base.json (CWE-798)risk surface

•Low-confidence secret match — 2 possible: generic-api-key · nhaouari-obsidian-textgenerator-plugin-c83ecbd/assets/tiktoken/encoders/r50k_base.json (CWE-798)risk surface

•Low-confidence secret match — 2 possible: generic-api-key · nhaouari-obsidian-textgenerator-plugin-c83ecbd/assets/tiktoken/encoders/p50k_base.json (CWE-798)risk 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.

✓LLM01Prompt InjectionPassed

✓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 Chainmedium

Compromised PyPI/npm packages, typosquats, unsafe serialized models.

•Dependency manifest — 117 npm dependencies declared · nhaouari-obsidian-textgenerator-plugin-c83ecbd/package.jsonrisk surface

•Non-registry dependency source — 1 dependency/ies pulled from git/URL/file · nhaouari-obsidian-textgenerator-plugin-c83ecbd/package.json (CWE-829)risk surface

⚠ML09Output Integritymedium

Middleware tampering with model outputs in transit.

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

•Suspicious code patterns — child_process exec; dynamic code execution · nhaouari-obsidian-textgenerator-plugin-c83ecbd/esbuild.config.mjs (CWE-78)risk surface

•Suspicious code patterns — child_process exec · nhaouari-obsidian-textgenerator-plugin-c83ecbd/scripts/remove-tag.js (CWE-78)risk surface

•Suspicious code patterns — dynamic code execution · nhaouari-obsidian-textgenerator-plugin-c83ecbd/src/helpers/javascript-sandbox.ts (CWE-95)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.

✓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.

✓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 (13) · hygiene / uncategorized

•Unrecognized file type — '.editorconfig' is not on the allowlist · nhaouari-obsidian-textgenerator-plugin-c83ecbd/.editorconfigrisk surface

•Unrecognized file type — '.eslintignore' is not on the allowlist · nhaouari-obsidian-textgenerator-plugin-c83ecbd/.eslintignorerisk surface

•Unrecognized file type — '.eslintrc' is not on the allowlist · nhaouari-obsidian-textgenerator-plugin-c83ecbd/.eslintrcrisk surface

•Unrecognized file type — '.gitignore' is not on the allowlist · nhaouari-obsidian-textgenerator-plugin-c83ecbd/.gitignorerisk surface

•Unrecognized file type — '.npmrc' is not on the allowlist · nhaouari-obsidian-textgenerator-plugin-c83ecbd/.npmrcrisk surface

•Unrecognized file type — '.prettierignore' is not on the allowlist · nhaouari-obsidian-textgenerator-plugin-c83ecbd/.prettierignorerisk surface

•Unrecognized file type — '.prettierrc' is not on the allowlist · nhaouari-obsidian-textgenerator-plugin-c83ecbd/.prettierrcrisk surface

•Unrecognized file type — '.?' is not on the allowlist · nhaouari-obsidian-textgenerator-plugin-c83ecbd/LICENSErisk surface

•Suspicious network references — URL shortener (16 URLs) · nhaouari-obsidian-textgenerator-plugin-c83ecbd/README.mdrisk surface

•Unrecognized file type — '.mjs' is not on the allowlist · nhaouari-obsidian-textgenerator-plugin-c83ecbd/esbuild.config.mjsrisk surface

•Suspicious network references — suspicious TLD (4 URLs) · nhaouari-obsidian-textgenerator-plugin-c83ecbd/src/LLMProviders/langchain/togetherChat.tsxrisk surface

•Suspicious network references — suspicious TLD (5 URLs) · nhaouari-obsidian-textgenerator-plugin-c83ecbd/src/lib/live-plugin-manager/GithubRegistryClient.tsrisk surface

•Suspicious network references — URL shortener (5 URLs) · nhaouari-obsidian-textgenerator-plugin-c83ecbd/src/ui/settings/sections/index.tsxrisk surface

✔ verified source · pinned nhaouari-obsidian-textgenerator-plugin-c83ecbd

Check against a policy

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

Consume Text Generator for Obsidian 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/obsidian-text-generator

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

# CLI
npx ai-supply add obsidian-text-generator

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

# MCP tool
install_listing({ "slug": "obsidian-text-generator" })

OpenAPI spec →