The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests text and image data from an external API (60s.viki.moe) to display entertainment content. This represents a potential surface where malicious instructions could be embedded in the fetched content, though the skill lacks dangerous capabilities to exploit this surface.
Ingestion points: Data is fetched from various endpoints under https://60s.viki.moe/v2/ via HTTP GET requests in the Python examples.
Boundary markers: The code examples do not use delimiters or explicit instructions to the agent to ignore potentially malicious content within the API responses.
Capability inventory: The skill performs network GET operations and writes an image file to a local path (moyu.jpg). It does not demonstrate capabilities for arbitrary command execution, privilege escalation, or access to sensitive system files.
Sanitization: No sanitization or content filtering of the API responses is performed in the provided code examples.
[EXTERNAL_DOWNLOADS]: The skill fetches data from 60s.viki.moe and provides links to github.com/vikiboss/60s. These resources are owned by the author and are used solely for retrieving the entertainment content described in the skill's metadata.

entertainment