Security audit

Narrative Quality Auditor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a scoped brand-narrative auditing guide that reads user-provided marketing evidence and only writes audit artifacts after explicit authorization.

Installers should expect this skill to inspect marketing canon, surfaces, and experiment evidence supplied or available in the working context. Allow persistence only when you want an audit report saved under the stated memory/audits/narrative path.

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The display name, summary, and description include Chinese text alongside English, but the skill does not state whether bilingual output is optional or user-selected. Because the instructions do not offer a language choice or explain a justified locale restriction, this can conflict with a policy requiring language or locale opt-in.

Static analysis

No suspicious patterns detected.