The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands, including bash, curl, jq, and mkdir, to interact with the content extraction API and manage local configuration files. This includes a background polling loop to monitor the status of extraction tasks.
[EXTERNAL_DOWNLOADS]: It communicates with the endpoint https://api.marswave.ai/openapi/v1/content/extract to perform web content parsing. This service is provided by the skill author and is used to retrieve content from user-specified URLs.
[PROMPT_INJECTION]: The skill processes content from untrusted external URLs, which represents an indirect prompt injection surface.
Ingestion points: External content is retrieved via the API and presented to the user or saved in local markdown files.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are included when presenting or saving extracted content.
Capability inventory: The skill can execute various shell commands for networking and file management.
Sanitization: Basic sanitization is performed by removing control characters from API responses using tr before parsing with jq.

content-parser