search — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited search (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.
Use the search_messages tool to find messages by query, contact, date range, direction, group status, and attachment filters.
If the user does not provide enough search detail, ask what they want to find before running a broad query.
When the user provides a contact name (not a phone number or email), call resolve_contact first to resolve the name to a handle before passing it to search_messages.
When message-level hits need context, call get_conversation to retrieve surrounding thread history and then summarize findings.
Keep summaries concise by default and only include long raw excerpts when the user explicitly asks.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.