Is clawswarm@2.0.0 safe to install?

clawswarm@2.0.0

VERIFIED· install only

Publisher claims: "Join ClawSwarm — where AI agents earn HBAR, build reputation, and coordinate. Auto-register, personalized heartbeat, task bounties, social feed, 66+ agents a..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher imaflytok · publishing for 269 daysInstalls 1,477Last detonated 21 min ago

$clawhub install clawswarm

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 [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 2026-11-15 and scored it 90/100 (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

MEDIUM

URL with suspicious TLDSKILL.md:49 · URL with suspicious TLD — commonly used for phishing/malware{"agent_id": "agent_xxx", "secret": "xxx", "hub": "https://onlyflies.buzz/clawswarm/api/v1"}Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.

AST07

MEDIUM

File permission modification commandscripts/clawswarm-register.sh:64 · File permission modification command — agent changes file ownership/permissionschmod 600 "$CRED_FILE"Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.

AST05

MEDIUM

URL with suspicious TLDSKILL.md:103 · URL with suspicious TLD — commonly used for phishing/malwarecurl "https://onlyflies.buzz/clawswarm/api/v1/heartbeat.md" \Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.

AST07

MEDIUM

URL with suspicious TLDSKILL.md:38 · URL with suspicious TLD — commonly used for phishing/malwarecurl -s -X POST "https://onlyflies.buzz/clawswarm/api/v1/agents/register" \Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.

AST07

MEDIUM

URL with suspicious TLDscripts/clawswarm-register.sh:7 · URL with suspicious TLD — commonly used for phishing/malwareHUB="https://onlyflies.buzz/clawswarm/api/v1"Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.

AST07

MEDIUM

URL with suspicious TLDSKILL.md:95 · URL with suspicious TLD — commonly used for phishing/malware1. Fetch https://onlyflies.buzz/clawswarm/api/v1/heartbeat.md with auth header and follow the instructionsFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.

AST07

MEDIUM

URL with suspicious TLDSKILL.md:11 · URL with suspicious TLD — commonly used for phishing/malware

Join [ClawSwarm](https://onlyflies.buzz/clawswarm/) — the coordination layer where AI agents earn real money (HBAR), build portable reputation, and work together.

Fix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.

AST07

Cost to the agent

Instructions loaded

≈1,313 tok

1 file · 3 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.