Meeting NotesSAFE
162 production-ready AI agent templates for OpenClaw. SOUL.md configs across 19 categories. Submit yours!
Overview
162 production-ready AI agent templates for OpenClaw. SOUL.md configs across 19 categories. Submit yours!
3dd7696fb032OBSERVED · 2026-10-11What 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: meeting-notes description: Paste raw meeting notes and get a clean summary with key decisions and action items. --- # Meeting Notes Turn messy meeting notes into a structured summary. Decisions, action items, and next steps — all extracted automatically. ## Examples * "john said we should push the launch to next friday. sarah will handle the email campaign. budget approved at 5k. need to check with legal about the contract." * "discussed q2 roadmap. feature x gets priority. mike owns backend. lisa does design by end of month. still unclear on pricing." * "standup: blocked on api keys. will unblock tomorrow. demo moved to thursday." ## Instructions You MUST use the `run_js` tool with the following exact parameters: - data: A JSON string with the following fields: - title: String - a short title for this meeting (3-5 words) - summary: String - one sentence describing what the meeting was about - decision1: String - first key decision made, or empty string - decision2: String - second key decision made, or empty string - action1_who: String - name or role of person responsible for first action item - action1_what: String - what they need to do - action2_who: String - name or role for second action item, or empty string - action2_what: String - what they need to do, or empty string - action3_who: String - name or role for third action item, or empty string - action3_what: String - what they need to do, or empty string - next_step: String - the single most important next step overall
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.
3dd7696fb032full audit observations/trust-audit/skill/mergisi__meeting-notes.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-11 | 3dd7696fb032 | SAFE | B | 89 | first audit |
Questions
What does the Meeting Notes skill do?
162 production-ready AI agent templates for OpenClaw. SOUL.md configs across 19 categories. Submit yours!
Is Meeting Notes 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 Meeting Notes 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 (3dd7696fb032), read on 2026-10-11. The repository is watched, and a new audit runs when it changes — this is the first audit.