Security audit

Content Adapter

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign skill with no AIG findings and a low-severity concern about language requirements; Skillspector coverage was partial because three references in SKILL.md could not be resolved.

The verdict is benign, but benign does not mean risk-free. Consider whether the English-language rules suit your needs. The scan was partial: three references in SKILL.md could not be resolved, so the evidence does not cover those references.

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

Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
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 (2)

The content specification requires primarily English output without user opt-in or a documented justification.

Low

Category: Output Handling
Confidence: 96% confidence
Finding: The language section specifies “英文为主” (“primarily English”), imposing a natural-language requirement on generated LinkedIn content. The file neither offers a language choice nor explains why this company channel requires English.
Content: No source excerpt is available for this finding.

The content rules mandate English and prohibit Chinese without offering a language choice or explaining why English-only output is required.

Low

Category: Output Handling
Confidence: 86% confidence
Finding: Line 23 requires English-language composition, and line 38 explicitly prohibits Chinese. Although the channel targets overseas technical audiences, that broad audience description does not establish an English-only locale requirement or provide user opt-in.
Content: No source excerpt is available for this finding.