Security audit

信息流

Security checks for vulnerabilities and agentic risk

Overview

This skill is a short feed-advertising planning guide and does not ask for hidden access, code execution, credentials, or persistent changes.

This appears safe to install as a general Chinese-language guide for feed-ad campaign planning and SOP work. Users should still treat it as guidance, verify platform and legal requirements independently, and keep any real advertising data access under their own normal account controls.

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

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (1)

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The description says the skill should be invoked '在开展信息流广告投放相关工作时调用' ('invoke when carrying out feed-advertising related work'), which is a broad condition without specific trigger phrases, exclusions, or scope limits. This could cause over-invocation across many general marketing tasks adjacent to feed-ad operations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.