The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill links to external resources on GitHub at github.com/mbzadev/skills. The repository owner name mbzadev is a character variation (omission of the 'a') of the stated author mabzadev, which is a pattern associated with typosquatting attempts for documentation or support resources.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it is instructed to read and process content from local project files (e.g., .agents/product-marketing.md) without defining boundary markers or sanitization procedures for the ingested data. * Ingestion points: .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md (referenced in SKILL.md). * Boundary markers: Absent; there are no instructions to the agent to treat this file content as untrusted data or to ignore embedded commands. * Capability inventory: The agent has the ability to read local filesystem contents and incorporate that information into its strategic advice and generated sequences. * Sanitization: Absent; the instructions do not specify any validation, filtering, or escaping of the ingested file content.

referrals