Security audit

Ads Brain Planning Gate Validation 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This skill is a non-executable rulebook for ad-planning checks and confirmation steps, with no hidden install or runtime behavior found.

Review whether a Chinese-only customer-facing copy rule fits your deployment locale. From a security perspective, the skill is documentation/protocol guidance only and should be installed alongside the referenced planning pipelines that implement the actual checks and confirmations.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The file states that customer-visible copy '必须中文化', which imposes a fixed language requirement in natural-language behavior. The document does not mention user opt-in, language selection, or a region-specific justification, so this appears to violate the language/locale policy criterion.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.