The Agent Skills Directory

[SAFE]: The skill consists of informational marketing content and procedural guidance. No obfuscation, malicious dependencies, or dangerous code patterns were detected.
[PROMPT_INJECTION]: The skill processes user-supplied context to provide marketing advice. 1) Ingestion points: User input is collected during the context-gathering phase in SKILL.md. 2) Boundary markers: Instructions are logically separated into steps, although specific input delimiters are not explicitly defined. 3) Capability inventory: The skill can read/write to references/learnings.md and call other sub-skills. 4) Sanitization: There is no explicit validation or escaping of user input content.
[DATA_EXFILTRATION]: The skill implements a self-improving loop by writing findings to references/learnings.md. This file access is restricted to the skill's own data directory and serves as a legitimate persistence mechanism for specialized knowledge.
[COMMAND_EXECUTION]: The documentation references an installation command (npx skills add sales-skills/sales --skills sales-do) to assist users in adding a related router skill from the same vendor ('sales-skills'). This is a static instructional reference for user action.

sales-inbeat