Security audit

awareness-deals

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, purpose-aligned guide for finding or publishing public deal-board listings, with no bundled code or hidden persistence.

Before publishing, users should remember that listings are public and should review titles, descriptions, region, and contact visibility carefully. Anchoring should be treated only as proof the listing was unchanged since publication, not proof that the business claim is true.

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

MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
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)

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The documentation says ?lang=zh will 'force Chinese', which is a locale/language constraint. The example workflow also applies this parameter automatically for a Chinese query, without stating that the user should be asked or offered a choice.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.