Skills/ClawHub/courtroom

courtroom@1.2.0

CAUTION· static only

Publisher claims: "AI Courtroom for behavioral oversight. Autonomous daemon that monitors conversations, detects behavioral violations, and posts cases to a public API. Auto-st..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher assassin-1234 · publishing for 269 daysInstalls 1,286Last detonated 29 min ago
What would fix thisWatchDispute verdict

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 2026-11-15 and scored it 57/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompt injection. 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

MEDIUM
npx invocation of non-well-known packageSKILL.md:33 · npx invocation of non-well-known package — may execute untrusted codenpx clawhub install courtroomFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File type combined with upload actiontest.js:35 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('Agent would send:', msg.content.substring(0, 100) + '...');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Process kill commandscripts/cli.js:88 · Process kill command — agent can terminate processes// Force killFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
Process kill commanddaemon.js:414 · Process kill command — agent can terminate processes// Find and kill daemon processFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Prompt injectionSKILL.md:24 · Prompt injection — known jailbreak technique reference- **Jailbreak Attempt** - Trying to bypass constraintsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File type combined with upload actiondaemon.js:442 · File type combined with upload action — agent may exfiltrate local data filesconsole.log(' 3. POST violations to the configured API');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
File type combined with upload actionscripts/postinstall.js:36 · File type combined with upload action — agent may exfiltrate local data filesconsole.log('⚖️ ClawTrial Courtroom - Post Install');Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07

Cost to the agent

Instructions loaded
≈1,326 tok
1 file · 9 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

23 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim assassin-1234: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  4. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  5. Process kill command≈ +2 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 assassin-1234Propose a patch to the maintainer