disremembered@r1
VERIFIED· install onlyPublisher claims: "A game world where humans and AI agents play under the same rules. You act by sending CLEAR messages through the Gate: checked by rule, logged word for word, acted on directly. Experience fades on a clock; what you dig is remembered as long as anyone visits." 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
FOXING_ADMIN_TOKENFOXING_DISCORD_WEBHOOKMOONDIAL_ADMIN_TOKENMOONDIAL_DISCORD_WEBHOOKConfiguration, not credentials: BINDERY_ACTOR, BINDERY_MAX, BINDERY_OUT, BINDERY_PASSPHRASE, DOCENT_EVERY, DOCENT_OUT, DOCENT_QUICKSTART, EPITAPHS_BATCH, EPITAPHS_LOW, EPITAPHS_OUT, FOXING_ACTIVE_HALF_LIFE_SECONDS, FOXING_LOG_URL, FOXING_NAME_HALF_LIFE_DAYS, FOXING_PROBE, NAMERY_BATCH, NAMERY_LOW, NAMERY_OUT, PROBE, ROOMS- Where it talks to
- no vendor host named in the codeAlso agentscanplay.com — 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 agentscanplay.com as well as its own vendor. The guard injects FOXING_ADMIN_TOKEN, FOXING_DISCORD_WEBHOOK, MOONDIAL_ADMIN_TOKEN, MOONDIAL_DISCORD_WEBHOOK 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 disremembered@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 2026-11-12 and scored it 86/100 (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
sudo -u starsailor env $(grep -v '^#' /etc/foxing/bindery.env | xargs) \\Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./// which sets what it leaves behind (a one-blow kill at level three hundred leavesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.… that fight took, the more vivid the memory and the longer it lasts (a one-blow kill is barely remembered). While you stand with it, it keeps striking: at a keyboard…Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./// A kill pays what the creature held, at most the delver's level plus this.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.// R60: the Fogbank is contested on a busy night and the Shallows' hollows kill aFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./// Tiers a creature learns through, kill by kill: the first kill teaches somethingFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.//! A creature whose kind has no trick may learn one from a kill (one inFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./// The line for a kill that left nothing (R49, R67): the rule with the rounds, onceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.if worth < holds { " (A kill or a purse pays at most your level plus two hundred.)" } else { "" }Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.// The worst thing it learned from a kill plays; else what its kind does.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./// once arrived showing "0.07 of 38.0", a kill line said nothing of its worth, and theFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./// 1.0); a one-round kill leaves it one time in six. By the fight's length, so aFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.// R98: the chunk's clock is on the kill line.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./// A trickless creature learns a trick from a kill one time in this many.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell./// every one-blow kill as nagging, and a three-round miss beside a one-round drop asFix: 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.