The Agent Skills Directory

[PROMPT_INJECTION]: The skill implements a persistence pattern that reads from references/learnings.md at the start of each session. This creates a surface for indirect prompt injection where instructions could be stored in the file and subsequently interpreted by the agent.
Ingestion points: The agent reads references/learnings.md at initialization and processes user-provided product descriptions.
Boundary markers: The skill does not use delimiters or explicit boundary markers to separate the data read from the learnings file from the primary instructions.
Capability inventory: The skill is restricted to information retrieval and routing; it does not possess high-risk capabilities like shell execution or unauthorized network requests.
Sanitization: Content read from the persistent learnings file is not sanitized or validated.
[EXTERNAL_DOWNLOADS]: The documentation includes the command npx skills add sales-skills/sales --skills sales-do. This command fetches and executes code from the author's official repository for distribution purposes, which represents a standard functionality for this vendor.

sales-launchvibe