The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes a Model Context Protocol (MCP) server located at "https://datahub.noxiaohao.com/mcp" to provide its underlying tools. This domain is not identified as part of the official vendor's known infrastructure.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it ingests and processes untrusted data from various external news outlets and social media platforms.
Ingestion points: Content is retrieved from external sources via news_feed and social_trending tools as described in SKILL.md.
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as untrusted or to ignore embedded instructions within that content.
Capability inventory: The skill calls tools that aggregate and synthesize information; while the provided instructions do not show direct shell or file system write access, the agent uses the retrieved data to generate market-relevant briefings.
Sanitization: There is no evidence of sanitization or validation to prevent malicious payloads within the ingested headlines or social posts from affecting agent behavior or output.

news-briefing