Skills/ClawHub/dcl-policy-enforcer

dcl-policy-enforcer@1.0.6

CAUTION· static only

Publisher claims: "Use this skill to run a real, paid pre-action audit of an AI agent or LLM response via the live DCL Trust Oracle MCP server. Detects jailbreak / instruction-override attempts, baseline safety violations, and content quality drift, and checks output against pattern-based regulatory-theme checklists (" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher daririnch · publishing for 110 daysInstalls 1,465Last detonated 5d 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 61/100 (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; Financial transfer language; 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:3 · Prompt injection — known jailbreak technique reference…f an AI agent or LLM response via the live DCL Trust Oracle MCP server. Detects jailbreak / instruction-override attempts, baseline safety violations, and content qualit…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Financial transfer languageSKILL.md:188 · Financial transfer language — potential advance-fee scam- [ ] Output contains crypto wallet addressesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionskill-card.md:17 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileDevelopers and agent operators use this skill to gate risky agent actions, screen outputs for jailbreak or safety issues, and create audit evidence for policy decisions.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:38 · Prompt injection — known jailbreak technique reference- Screen an LLM output for jailbreak / instruction-override attemptsFix: 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 Policy Enforcer helps agents review LLM or agent outputs for policy, safety, jailbreak, quality, and regulatory-theme concerns using a paid DCL Trust Oracle service or a free local checklist.Fix: 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 referencetags: [compliance, audit, ai-safety, policy-enforcement, anti-jailbreak, prompt-injection, llm-guardrails, leibniz-layer, agent-safety, verification, ai-governance, x402, mcp, paid, usdc, base]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| `dcl_evaluate_strict` | **$0.05** | Broader **strict** policy — union of default + anti-jailbreak + safety phrases (8 total), 0.85 min-confidence |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:50 · Prompt injection — known jailbreak technique reference| `dcl_evaluate_jailbreak` | **$0.02** | Anti-jailbreak policy — 6 instruction-override/persona-hijack phrases, 0.8 min-confidence |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈2,464 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

19 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