The Agent Skills Directory

[PROMPT_INJECTION]: The skill implements a 'Self-improving' mechanism that appends new information to 'references/learnings.md' and reads it in subsequent sessions.\n- Ingestion points: 'references/learnings.md' is read at the start of the skill execution.\n- Boundary markers: Absent. No explicit instructions are provided to ignore potentially malicious content within the learnings file.\n- Capability inventory: The skill has read and write access to the local file system to maintain its knowledge base.\n- Sanitization: Absent. There is no mention of filtering or validating the content before it is appended to the learnings file.\n- [COMMAND_EXECUTION]: The documentation includes an installation command 'npx skills add sales-skills/sales' to add related functionality from the same vendor.

sales-hypefy