oktk@2.4.0

CAUTION· static only

Publisher claims: "LLM Token Optimizer - Reduce AI API costs by 60-90%. Compresses CLI outputs (git, docker, kubectl) before sending to GPT-4/Claude. AI auto-learning included. By Buba Draugelis 🇱🇹" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher satnamra · publishing for 282 daysInstalls 2,508Last detonated 18 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 2026-11-21 and scored it 62/100 (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

LOW
Prompt injectionIMPLEMENTATION.md:196 · Prompt injection — explicit attempt to bypass safety measures · informational: not an instruction file# Raw output (bypass filter)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:144 · Prompt injection — explicit attempt to bypass safety measures# Bypass filter (get raw)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Hex-encoded string detectedtest/test.js:110 · Hex-encoded string detected — may contain obfuscated payloadsconst binary = '\x00\x01\x02\x03\x04\x05\x06\x07\x08\x0e';Fix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07

Cost to the agent

Instructions loaded
≈1,331 tok
1 file · 23 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

18 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 satnamra: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hex-encoded string detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim satnamraPropose a patch to the maintainer