hearsay@0.1.0
VERIFIED· install onlyPublisher claims: "Checks media-plan taste claims against Qloo audience data and returns a verdict per pick with the audience's real preferences. Also exposes what fans of one thing love in another category, so agents can validate picks before spending ad money." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.
Before you give it your token
- It will ask for
DATABASE_URLQLOO_API_KEYConfiguration, not credentials: HEARSAY_IP_SALT, HEARSAY_LIVE, PGLITE_DIR, QLOO_API_URL, QLOO_BUDGET_FLOOR, QLOO_CALLS_PER_DAY, VERCEL- Where it talks to
- no vendor host named in the codeAlso iab.com, qloo.test — not the publisher's domain; check what for before connecting.
- What the honeypot saw
- no credential files read · no network
- What we could not test
- use of the skill by an agent
Connect it with a scoped credential, under the guard, and read the third-party hosts first. The code names iab.com, qloo.test as well as its own vendor. The guard injects DATABASE_URL, QLOO_API_KEY only into requests to the host you bind (and its subdomains) and refuses the rest.
Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-11 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 · 1 scenarios · 0 deviationsStatic findings
expect(cleanText(`Kate Bush${hidden}`, 100)).toBe("Kate Bush");Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.return Response.json({ error: "bad_input", message: "Send JSON." }, { status: 400 });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.const INVISIBLE = /[\u{E0000}-\u{E007F}----]/gu;Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.if (text.length > MAX_BODY) return Response.json({ error: "bad_input", message: "Request too large." }, { status: 413 });Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.const padded = "".repeat(5000) + "Kate Bush 🎵 rules";Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.await handleCheck({ ...PLAN, brand: "Rockstar Games" }, ip("1.2.3.4"), d);Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.const INVISIBLE = /[\u{E0000}-\u{E007F}----]/gu;Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.expect(cleanText(`Kate Bush${hidden}`, 100)).toBe("Kate Bush");Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.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.