The Agent Skills Directory

[Data Exposure & Exfiltration] (SAFE): The skill references a local file .claude/product-marketing-context.md to gain business context. This is a standard pattern for agent personalization and does not involve accessing sensitive system files or credentials. No network operations (exfiltration) were found.
[Remote Code Execution] (SAFE): No executable scripts, command-line operations, or package installations are present in the skill.
[Indirect Prompt Injection] (LOW): The skill has a data ingestion point via the .claude/product-marketing-context.md file. While this is a surface for indirect injection if an attacker can control that file, the skill lacks any dangerous capabilities (like network access or command execution) to escalate such an injection, rendering the risk minimal.
[Obfuscation] (SAFE): All content is provided in plain markdown text with no encoded or hidden characters.

programmatic-seo