The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill performs network GET requests to fetch news articles from skills.myzaker.com. This is a legitimate functional requirement for a news-gathering skill and targets the vendor's official service domain.
[INDIRECT_PROMPT_INJECTION]: The skill ingests and displays untrusted data (news headlines and summaries) from an external source, which represents a standard but inherent surface for indirect prompt injection.
Ingestion points: Articles are fetched via the get_category_articles tool defined in SKILL.md and implemented in scripts/get_category.py.
Boundary markers: The skill does not employ specific boundary markers or isolation delimiters to wrap the external news content when presenting it to the agent.
Capability inventory: The skill's capabilities are restricted to network GET requests and basic terminal output; it does not include file-writing, privilege escalation, or shell execution capabilities.
Sanitization: No explicit sanitization or filtering is applied to the fetched article metadata (titles, summaries) before it is processed by the agent.

zaker-category-news