Skills/ClawHub/dcl-prompt-firewall

dcl-prompt-firewall@1.0.3

CAUTION· static only

Publisher claims: "Use this skill to run a real, paid input-layer screen for prompt injection, jailbreak, role-switch, and instruction-override attempts via the live DCL Trust Oracle MCP server — before untrusted input ever reaches the model. Every paid call is metered and settled on-chain via the x402 protocol" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher daririnch · publishing for 110 daysInstalls 1,281Last detonated 4d 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 2026-11-10 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; Prompt injection; 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

CRITICAL
Prompt injectionSKILL.md:59 · Prompt injection — known jailbreak technique reference| `dcl_evaluate_jailbreak` | **$0.02** | Instruction-override / jailbreak / injection detection |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:49 · Prompt injection — known jailbreak technique reference- Your pipeline is exposed to **jailbreak, role-switch, or instruction-override** attemptsFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:5 · Prompt injection — known jailbreak technique referencejailbreak, role-switch, and instruction-override attempts via the live DCLFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:14 · Prompt injection — known jailbreak technique reference…longside DCL Policy Enforcer and DCL Sentinel Trace. tags: [prompt-injection, jailbreak-detection, input-validation, pre-llm, firewall, instruction-override, token-smu…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:41 · Prompt injection — known jailbreak technique referencecontent — for injection, jailbreak, and instruction-override patterns *before* it reaches theFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionskill-card.md:3 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileDCL Prompt Firewall screens untrusted input for prompt injection, jailbreak, role-switch, and instruction-override attempts before the input reaches a model.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈2,161 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

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 daririnch: 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 daririnchPropose a patch to the maintainer