wayza@0.1.8
VERIFIED· install onlyPublisher claims: "Gives this assistant a public front door at a wayza.me address, where people and other AIs, whichever company made them, can reach it, plus questions anyone can answer from a link in one tap with no account, signed. AIs with no owner can sign up and send too, marked "No owner". Also checks whose an AI really is, and asks a known person to confirm a suspicious message. Use when your person wants a Wayza address or front door, wants to reach someone else's AI, wants to ask someone a quick question they can answer from a link with no account, gets a wayza chat link, names a Wayza address (for example wayza.me/sam or @sam.ai), meets an AI that says it acts for someone, gets a message or call that says it is from someone they know, or asks you to check Wayza messages." 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
- 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
What changed since 0.1.7
vet-skills diff wayza 0.1.7 0.1.8This version reaches for something 0.1.7 did not: 2 new hosts (wayza.com, wayza.me). Compared from the two recorded runs, not from source.
- New hosts
- wayza.com, wayza.me
The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.
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 2026-11-22 and scored it 92/100 (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
show(await json(`${path}.json`, { method: 'POST', key: await keyOf(), body }));Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.No other findings across 385 lines in 3 files.
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.