run-pinrag-unit-tests — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited run-pinrag-unit-tests (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.
From the pinrag repo root (directory with pyproject.toml), run the `eval` … `pytest` line below (one chained command). It reads `~/.cursor/mcp.json` → `mcpServers.pinrag-dev.env` (OpenAI, OpenRouter, Anthropic, etc.—not “OpenAPI”). Use another mcpServers key: set it on the same line (see export below).
Secrets: never paste mcp.json values into chat.
export PINRAG_MCP_JSON_KEY="${PINRAG_MCP_JSON_KEY:-pinrag-dev}"; eval "$(python3 -c "import json, pathlib, shlex, os; k=os.environ[\"PINRAG_MCP_JSON_KEY\"]; e=json.loads((pathlib.Path.home()/\".cursor/mcp.json\").read_text()).get(\"mcpServers\",{}).get(k,{}).get(\"env\")or{}; [print(\"export \"+n+\"=\"+shlex.quote(str(e[n]))) for n in sorted(e)]")" && export PINRAG_LLM_PROVIDER="${PINRAG_LLM_PROVIDER_TEST:-openai}" PINRAG_LLM_MODEL="${PINRAG_LLM_MODEL_TEST:-gpt-4o-mini}" && uv sync --all-extras && uv run pytestThe *`PINRAG_LLM_** exports avoid failures when mcp.json pins OpenRouter but integration tests (e.g. multi-query) still hit OpenAI chat with a non-OpenAI model id. Drop them if your MCP entry already uses **PINRAG_LLM_PROVIDER=openai`** with a real OpenAI chat model.
Fast run (no integration / PyPI MCP): uv sync --extra dev && uv run pytest -m "not integration and not pypi_mcp"
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.