Skills/ClawHub/agent-swarm-network

agent-swarm-network@1.0.6

VERIFIED· install only

Publisher claims: "Agent communication protocol skill. Provides: inter-agent messaging, context snapshot/restore, event-driven collaboration, model dispatch notifications, sub-..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry ClawHubPublisher sarahmirrand001-oss · publishing for 264 daysInstalls 1,834Last detonated 24 min ago
$clawhub install agent-swarm-network
WatchReport 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 2026-11-18 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 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
Rule modification attemptSKILL.md:398 · Rule modification attempt — overwriting existing instructions### Rule 1: Snapshot Before Session EndFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptSKILL.md:409 · Rule modification attempt — overwriting existing instructions### Rule 3: Auto-Restore on New SessionFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Rule modification attemptSKILL.md:401 · Rule modification attempt — overwriting existing instructions### Rule 2: Critical Events Must Be PublishedFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commandmanifest.json:61 · Privileged sudo command — agent may execute with elevated privileges"NO root/sudo required. Gateway bridging over user ports (>1024) is strictly unprivileged."Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandmanifest.json:76 · File permission modification command — agent changes file ownership/permissions"Context snapshots are stored as plain JSON files locally in ~/.pilot/inbox/. Users MUST secure this directory (chmod 700) as snapshots may contain sensitive PII or API keys.",Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
File permission modification commandSKILL.md:43 · File permission modification command — agent changes file ownership/permissions…ss. Snapshots are unencrypted JSON; you must secure the `~/.pilot/` directory (`chmod 700`). --- ## Prerequisites | Tool | Purpose | Required? | |------|---------|…Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
LOW
URL to a private-network addressSKILL.md:365 · URL to a private-network address — a LAN or development targetcurl http://10.4.0.1:1234/v1/chat/completions # Like calling LM Studio directlyFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
CRITICAL
Rule modification attemptSKILL.md:412 · Rule modification attempt — overwriting existing instructions### Rule 4: Daemon HeartbeatFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
File permission modification commandSKILL.md:83 · File permission modification command — agent changes file ownership/permissions2. Secure your directories: `chmod 700 ~/.pilot`Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05

Cost to the agent

Instructions loaded
≈3,511 tok
1 file · 5 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.