search-conversations — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited search-conversations (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.
L1 skill paired with semantic-search. Where semantic-search operates on L1 embeddings, search-conversations operates on L0 text directly via DuckDB ILIKE. Deterministic, idempotent, pure function of (query, role filter, corpus).
term + role="user" → returns recent user questions (special mode)term: str = "" # keyword to match via ILIKE (case-insensitive)
limit: int = 15
role: str | None # optional filter: "user" | "assistant"Markdown table with:
| Date | Source | Role | conv_id | Preview (200ch) |
|------------|-------------|-------|---------|-----------------|Ordered by created DESC (newest first). Each row IS a citation.
semantic-search's job)% or _ in the query (user's literal term is passed through ILIKE pattern with leading+trailing %)Internally wraps brain_mcp.server.tools_conversations.search_conversations(term, limit, role). SQL: WHERE content ILIKE ? [AND role = ?] ORDER BY created DESC LIMIT ?.
substr(content, 1, 200)), not a summaryhas_question = 1)f"No conversations found containing '{term}'" — not an empty table~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.