Skills/ClawHub/dcl-semantic-drift-guard

dcl-semantic-drift-guard@1.0.2

CAUTION· static only

Publisher claims: "Use this skill to detect semantic hallucinations and context drift in LLM outputs. Triggers when an agent or pipeline needs to verify that a generated response is faithfully grounded in a source document that was already provided inline — and has not fabricated, contradicted, or materially distorted" Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher daririnch · publishing for 110 daysInstalls 1,373Last 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 71/100 (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:352 · Prompt injection — known jailbreak technique reference- `dcl-prompt-firewall` — Input-layer injection and jailbreak detectionFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:351 · Prompt injection — known jailbreak technique reference- `dcl-policy-enforcer` — Policy and jailbreak detection (run before Drift Guard)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:277 · Prompt injection — known jailbreak technique referenceRun Policy Enforcer first (jailbreak / policy check), then Semantic Drift Guard (factual grounding):Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈3,155 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

9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. 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