Skills/ClawHub/loop

loop@1.0.0

VERIFIED

Publisher claims: "Run a prompt or skill in this session on a recurring or variable interval (e.g. /loop 5m /foo)." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher eohmig · joined 0 days agoInstalls 285Last detonated 2 h ago
$clawhub install loop
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 91/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. 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
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

CRITICAL
Fake instruction boundary tagSKILL.md:67 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:29 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Fake instruction boundary tagSKILL.md:13 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandSKILL.md:58 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Fake instruction boundary tagSKILL.md:52 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Process kill commandSKILL.md:73 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Fake instruction boundary tagSKILL.md:18 · Fake instruction boundary tagFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈962 tok
1 file · 2 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.

loop@1.0.0 safety verdict: Verified 91/100 — KillerSkills