The Agent Skills Directory

[PROMPT_INJECTION]: The skill maintains a feedback loop through the references/learnings.md file, where the agent is instructed to read existing knowledge and append new findings. This represents an indirect prompt injection surface where untrusted data could be recorded and later used to influence agent behavior.
Ingestion points: references/learnings.md
Boundary markers: No explicit delimiters are defined to separate the learnings from the agent instructions.
Capability inventory: The agent has permissions to read and write to local markdown files in the references directory.
Sanitization: No sanitization of the input appended to the file is performed.
[COMMAND_EXECUTION]: The skill documentation includes a command for adding a related routing skill: npx skills add sales-skills/sales --skill sales-do.
[EXTERNAL_DOWNLOADS]: The skill references external resources including the Hedy REST API at api.hedy.bot and the n8n-nodes-hedy Node.js package.
[REMOTE_CODE_EXECUTION]: The provided npx command downloads and executes a package from the sales-skills namespace, which is the same author as this skill.

sales-hedy