risk-analyst-agent — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited risk-analyst-agent (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.
RISKMODELS_API_KEY=… npx -y riskmodels@latest installriskmodels_* over inventing REST paths| Goal | Tool |
|---|---|
| Single-name L3 snapshot | riskmodels_decompose or chat get_risk_metrics |
| Compare names | riskmodels_compare |
| Weighted portfolio | riskmodels_portfolio_decompose / compute_portfolio_risk_index |
| Deterministic chart/table JSON | riskmodels_render_artifact |
| Resolve fund | search_funds → BW-FUND-… |
| Resolve 13F filer | search_filers → BW-FILER-… |
top_holdings_erm_stacked, cumulative_return_strip, narrative_profile, narrative_perf_insight, narrative_risk_insight, plus filer panels (entity_header, risk_summary_panel, …)BW-FUND-*, BW-FILER-*, or BW-PORTFOLIO-* with subject_payload.positions for pasted bookslatest for funds; filers often need explicit YYYY-MM-DDjson for chat (default); png/svg return base64[0,1].Full README: examples/agents/risk-analyst-agent/README.md in RiskModels_API.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.