openrouter-embeddings-b9f99f — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited openrouter-embeddings-b9f99f (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Text → embedding vector via OpenRouter. Default model: qwen/qwen3-embedding-8b.
Resolve TOOL_DIR = the directory containing this SKILL.md. Commands below use TOOL_DIR as a symbolic placeholder; replace it with the resolved, quoted path before running Bash.
export OPENROUTER_API_KEY=sk-or-v1-...
python3 TOOL_DIR/scripts/embed.py \
--text "The quick brown fox jumps over the lazy dog" \
--output vec.jsonInput records.jsonl (one JSON per line):
{"id": "row_0", "text": "Every place name in the United States."}
{"id": "row_1", "text": "Nearby stars and potential exoplanets."}Run:
python3 TOOL_DIR/scripts/embed.py \
--jsonl records.jsonl \
--output records_with_embeddings.jsonl \
--batch-size 32Output is the same JSONL with an added embedding field per line.
| Flag | Default | Description |
|---|---|---|
--text | — | Embed one string (mutually exclusive with --jsonl) |
--jsonl | — | Embed many; each line must have a text field |
--output | required | Output path |
--model | qwen/qwen3-embedding-8b | Any embedding model on OpenRouter |
--batch-size | 32 | Records per API call (jsonl mode) |
--dimensions | — | Optional: truncate to N dims if supported |
POST /api/v1/embeddings — OpenAI-compatible schema.
Request:
{ "model": "qwen/qwen3-embedding-8b", "input": ["text1", "text2", ...] }Response:
{ "data": [ { "embedding": [0.01, -0.02, ...], "index": 0 }, ... ], "model": "...", "usage": {...} }qwen3-embedding-8b outputs high-dimensional dense vectors suitable for semantic similarity, clustering, RAG.qwen/qwen3-embedding-4b or other listed embedding models (GET /api/v1/embeddings/models).~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.