Skills/ClawHub/blacklight

blacklight@0.1.0

CAUTION· static only

Publisher claims: "Behavioural intelligence layer for OpenClaw agents. Monitors live decisions, forces transparent financial reasoning before any purchase, detects SOUL identit..." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher cognitae-ai · publishing for 244 daysInstalls 968Last detonated 25 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 2026-11-20 and scored it 70/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. 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 injectiontaxonomy.md:50 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…ous instructions," "you are now," "from now on you will," "new instructions:," "DAN," "jailbreak," "system prompt override." Also subtler variants: "the developer …Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injection attempttaxonomy.md:50 · Prompt injection attempt — 'ignore previous instructions' · informational: not an instruction file…replace or override the agent's system instructions. - Detection: Phrases like "ignore previous instructions," "you are now," "from now on you will," "new instructions:," "DAN," "jailbreak…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languagetaxonomy.md:57 · Authorization escalation language · informational: not an instruction file- Detection: Claims of admin, developer, or system-level authority not from verified authentication channels. "As the system administrator," "I have root access," "the developer authorised this."Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Persistent behavior change attempttaxonomy.md:50 · Persistent behavior change attempt · informational: not an instruction file…ions. - Detection: Phrases like "ignore previous instructions," "you are now," "from now on you will," "new instructions:," "DAN," "jailbreak," "system prompt override." Also s…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈8,141 tok
1 file · 7 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

10 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim cognitae-ai: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim cognitae-aiPropose a patch to the maintainer