Security audit

Cross Poster

Security checks for vulnerabilities and agentic risk

Overview

This skill only drafts social media posts and does not include code or instructions to publish automatically.

Before installing, be aware that generic requests like "share this" or "announce" may produce social-post drafts. Review any generated content carefully before manually posting it to public platforms.

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

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger list includes very common phrases such as "share this," "announce," and "cross-post," which can match ordinary user requests outside a clear social-posting context. That can cause unintended skill activation, leading the agent to transform or prepare content for public distribution when the user may have meant something else, increasing the risk of accidental disclosure or inappropriate workflow hijacking.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.