The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches feature documentation and setup guides from the official Wasp repository on GitHub (github.com/wasp-lang/wasp). This is a standard and expected operation for a tool designed to facilitate framework-specific configurations.
[INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection because it is designed to fetch and follow external installation guides. This risk is inherent to the skill's primary purpose and is mitigated by the use of trusted vendor sources.
Ingestion points: Feature-specific setup guides are retrieved from raw.githubusercontent.com/wasp-lang/wasp/... in the styling.md, authentication.md, email-provider.md, and database.md files.
Boundary markers: There are no explicit boundary markers or instructions to the agent to disregard potentially malicious instructions within the fetched data.
Capability inventory: The skill is designed to modify Wasp configuration files (main.wasp or main.wasp.ts) and follow installation steps, which may involve executing shell commands.
Sanitization: The skill does not implement specific sanitization or validation steps for the external content before it is processed by the agent.

add-feature