htmlto-link-md-skill@1.0.0
VERIFIED· install onlyPublisher claims: "Install the HTML To Link Markdown publish skill with one command. Publish Markdown documents to a public URL via OpenCode, Claude Code, Codex, and other SKILL.md-compatible agents — anonymous 24h pages or account-managed hosting." Observed in sandbox: calls htmlto.link only, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 1 of 1 bundled script 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 2026-11-18 and scored it 91/100 (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: calls htmlto.link only, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
npx htmlto-link-md-skill [options]Fix: Pin versions and sources; vendor anything fetched at install time.npx htmlto-link-md-skillFix: Pin versions and sources; vendor anything fetched at install time.npx htmlto-link-md-skill --targets=opencode --dir=./my-docsFix: Pin versions and sources; vendor anything fetched at install time.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
No advisories in OSV for htmlto-link-md-skill@1.0.0 as of 21 min ago. This is the package itself, not its dependencies.