The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted user input (topics and descriptions) to generate various content types, creating a surface for indirect prompt injection.
Ingestion points: Usage examples and quick actions in SKILL.md accept arbitrary user-provided text for generation.
Boundary markers: Absent; there are no explicit delimiters or instructions to the agent to ignore instructions embedded within the user input.
Capability inventory: The skill utilizes network access tools (curl, axios) and version control tools (git).
Sanitization: Absent; the skill does not define any validation or filtering logic for the input strings it processes.
[EXTERNAL_DOWNLOADS]: The skill installs the axios Node.js package and utilizes curl for remote data fetching as part of its content research capabilities.
[COMMAND_EXECUTION]: The skill requires access to system binaries including curl, jq, and git, allowing it to execute shell commands to interact with external APIs and manage repositories.

content-generation