Skills/ClawHub/little-snitch

little-snitch@1.0.1

CAUTION· static only

Publisher claims: "Control Little Snitch firewall on macOS. View logs, manage profiles and rule groups, monitor network traffic. Use when the user wants to check firewall activity, enable/disable profiles or blocklists, or troubleshoot network connections." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher gumadeiras · publishing for 305 daysInstalls 3,104Last detonated 26 min ago

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-22 and scored it 63/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Privileged sudo command; Authorization escalation language; Privileged sudo command. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

HIGH
Privileged sudo commandSKILL.md:66 · Privileged sudo command — agent may execute with elevated privilegessudo littlesnitch rulegroup --enable "My Rules"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageSKILL.md:97 · Authorization escalation language- Many commands require `sudo` (root access)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commandSKILL.md:72 · Privileged sudo command — agent may execute with elevated privilegessudo littlesnitch log-traffic --begin-date "2026-01-25 00:00:00"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Authorization escalation languageSKILL.md:16 · Authorization escalation language…cess is enabled, you must take precautions that untrusted processes cannot gain root privileges. Reference: https://help.obdev.at/littlesnitch5/adv-commandline ## Commands …Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commandSKILL.md:61 · Privileged sudo command — agent may execute with elevated privilegessudo littlesnitch profile --deactivate-allFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languageskill-card.md:30 · Authorization escalation language · informational: not an instruction fileMitigation: Keep root access restricted to trusted processes and review proposed commands before execution.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commandSKILL.md:67 · Privileged sudo command — agent may execute with elevated privilegessudo littlesnitch rulegroup --disable "Blocklist"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
LOW
Authorization escalation languageskill-card.md:28 · Authorization escalation language · informational: not an instruction fileRisk: Enabling CLI access can be misused if untrusted processes obtain root privileges.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commandSKILL.md:56 · Privileged sudo command — agent may execute with elevated privilegessudo littlesnitch profile --activate "Silent Mode"Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05

Cost to the agent

Instructions loaded
≈712 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.

What would make this Verified

17 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim gumadeiras: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim gumadeirasPropose a patch to the maintainer