Book CatalogSAFE
An Aspire reference architecture for cloud-native microservices and agentic AI with MCP, A2A & AG-UI
Overview
An Aspire reference architecture for cloud-native microservices and agentic AI with MCP, A2A & AG-UI
07c2bf555f06OBSERVED · 2026-10-14What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: book-catalog description: Search and recommend books from BookWorm's catalog. Use when customers ask about finding books, getting personalized recommendations, exploring genres, discovering authors, or comparing titles. metadata: author: Nhan Nguyen version: "1.0" license: MIT --- # Book Catalog ## Search Capabilities Use the `search_catalog` tool to find books. The catalog supports: | Filter | Examples | |------------------|-------------------------------------------| | Title keyword | "clean code", "dune" | | Author name | "Martin Fowler", "Frank Herbert" | | Genre / category | "science fiction", "software engineering" | | Price range | min/max price filters | | Rating | minimum star rating | | Availability | in-stock only | ## Recommendation Strategy 1. **Clarify preferences** — Ask about genre, favorite authors, reading level, or purpose (gift, self-learning, leisure). 2. **Search first** — Always use `search_catalog` before recommending; never invent titles. 3. **Rank results** — Prefer higher ratings, then popularity, then price. 4. **Provide context** — Include author, genre, a one-sentence description, and price. 5. **Suggest alternatives** — Offer 2–3 options when possible. ## Response Format - Present books as a numbered or bulleted list. - Include: **Title** — _Author_ — Genre — ⭐ Rating — 💲 Price. - If no results, say so and offer to broaden the search. ## Handoff Rules - Policy or account questions → hand off to QAAgent. - Emotional feedback or complaints → hand off to SentimentAgent. - Complete ongoing book task before any handoff. For catalog browsing tips and genre descriptions, see [references/CATALOG_GUIDE.md](references/CATALOG_GUIDE.md). For a sample book listing template, see [assets/book-listing-template.md](assets/book-listing-template.md).
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | NA |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
07c2bf555f06full audit observations/trust-audit/skill/foxminchan__book-catalog.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-14 | 07c2bf555f06 | SAFE | B | 89 | first audit |
Questions
What does the Book Catalog skill do?
An Aspire reference architecture for cloud-native microservices and agentic AI with MCP, A2A & AG-UI
Is Book Catalog safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can Book Catalog access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
How current is this page?
The grade is for one exact copy of the source (07c2bf555f06), read on 2026-10-14. The repository is watched, and a new audit runs when it changes — this is the first audit.