The Agent Skills Directory

[SAFE]: The skill operates within its intended scope of providing sales advice and strategy. It utilizes local reference files (references/learnings.md, references/platform-guide.md) for knowledge management and documentation, which is standard behavior for this type of agent extension.\n- [COMMAND_EXECUTION]: The skill mentions an installation command (npx skills add ...) for related skills. This command targets the official vendor repository (sales-skills) and is a standard procedure within this platform ecosystem to extend agent capabilities.\n- [PROMPT_INJECTION]: The skill implements a self-improving mechanism by reading and writing to references/learnings.md. This creates an indirect prompt injection surface where untrusted user data could influence future sessions. However, given the skill's low-privilege capabilities (primarily information retrieval), this surface is considered safe. Ingestion points: references/learnings.md and user input; Boundary markers: Absent; Capability inventory: File read/write; Sanitization: Absent.

sales-digital-products