The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (ls) on specific local paths to identify whether recommended companion skills are installed. This behavior is used to provide installation suggestions for related tools from the same author.
[EXTERNAL_DOWNLOADS]: The documentation recommends the installation of related skills via the npx skills add command. These recommendations point to official repositories belonging to the vendor (AbsolutelySkilled).
[PROMPT_INJECTION]: The skill processes external product data and metrics provided by the user, which presents a surface for indirect prompt injection. No specific boundary markers or sanitization rules are defined for this untrusted input.
Ingestion points: User-provided event names, metrics frameworks, and funnel descriptions during analysis (SKILL.md).
Boundary markers: Absent; the skill does not define specific delimiters for separating untrusted user data from agent instructions.
Capability inventory: Local file system discovery via ls and package installation via npx (SKILL.md).
Sanitization: Absent; the skill lacks explicit instructions to validate or escape user-supplied strings before processing.

product-analytics