skillnote@0.5.4
VERIFIED· install onlyPublisher claims: "Self-hosted skill registry for OpenClaw. Stores procedures your team writes (name, description, body), syncs them to disk before each task, and collects whic..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 2 of 2 bundled scripts run with no arguments, with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-19 and scored it 81/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationsStatic findings
| Port `8082` busy | `npx skillnote start --api-port 8182` |Fix: Pin versions and sources; vendor anything fetched at install time.| Bind to a LAN IP | `SKILLNOTE_HOST=<your-lan-ip> npx skillnote start` |Fix: Pin versions and sources; vendor anything fetched at install time.- If still unreachable after 3 retries spaced 5s apart: ask the user to share the last 20 lines of `npx skillnote start` output; surface their error verbatim; stop.Fix: Pin versions and sources; vendor anything fetched at install time.> npx skillnote startFix: Pin versions and sources; vendor anything fetched at install time.echo "SkillNote: updated $SIDECAR (add '@include ~/.openclaw/skillnote-agents.md' to your AGENTS.md once)"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.curl -sf $SKILLNOTE_BASE_URL/setup/agent | bash -s -- --agent openclawFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.# AGENTS.md (one-time setup; see SKILL.md). We do NOT modifyFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.kill -0 "$_pid" 2>/dev/null || breakFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.curl -sf $SKILLNOTE_BASE_URL/setup/agent | bash -s -- --agent openclawFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.> Open `~/.openclaw/workspace/AGENTS.md` and delete the line `@include ~/.openclaw/skillnote-agents.md`. (I won't auto-edit your AGENTS.md.)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.…p 6 | | `0` or file missing | Ask the user (once, explicit consent): "I need to add one line to your `~/.openclaw/workspace/AGENTS.md` so OpenClaw picks up the SkillNote instructions: `@include ~/.openclaw/skillno…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.| Port `3000` busy | `npx skillnote start --web-port 3001` |Fix: Pin versions and sources; vendor anything fetched at install time.…the user to say "re-setup skillnote" so they consent explicitly. - **Don't auto-edit AGENTS.md.** sync.sh writes the sidecar `~/.openclaw/skillnote-agents.md`; adding the `@include` line to AGENTS.md is a one-time user-consented edit (St…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Modify the user's AGENTS.md (this is intentional; v0.4.0 did this, v0.4.1 stopped — see commit log)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.# Stale args (old per-agent path from pre-0.4.0) — kill + relaunch.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.chmod +x ~/.openclaw/skills/skillnote/sync.sh && ~/.openclaw/skills/skillnote/sync.shFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.# ── Write skillnote-agents.md sidecar (idempotent, runs every sync) ───────────Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.kill "$_pid" 2>/dev/nullFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.