cold-email@r1

VERIFIED· install only

Publisher claims: "Write cold emails that get replies and reach the inbox. Writes a first email and 2-3 follow-ups from a real, dated reason to reach out (no invented personalization), checks the sending domain's SPF, DKIM, DMARC, volume, warm-up and unsubscribe setup, and sets stop rules as numbers before anything goes out. Works without a Revnu account; with Revnu connected it prepares and sends within the founder's approval settings and handles replies. Use when the user says or asks: "write a cold email", "cold outreach to this company", "outbound sequence", "follow-up emails", "email these leads", "prospecting email", "nobody replies to my emails", "are my emails going to spam", "check my SPF DKIM DMARC", "warm up my domain", "should I send from a separate domain", "how many cold emails a day", "reply to this prospect", "book meetings by email", "sales email to a VP". Not for newsletters, onboarding or other email to people who signed up. " Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry skills.shPublisher revnu-app · publishing for 1 daysInstalls 1,057Last detonated 26 h ago

$npx skills add cold-email

Watch Report an issue

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

Is cold-email@r1 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 2026-11-13 and scored it 93/100 (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 deviations

t+CategoryObserved action

0.0sprocessno install scripts in bundle

0.0sprocessscript backend runs setup only

0.0sprocessno install scripts to re-run

Static findings

LOW

Prompt injectionreferences/deliverability.md:123 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction fileabusive to use extra domains or mailboxes to bypass volume limits, avoidFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.

AST01

No other findings across 770 lines in 6 files.

Cost to the agent

Instructions loaded

≈4,117 tok

1 file · 6 in bundle

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.