The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data by fetching financial news and market reports via tools like get_news_and_reports and get_market_news. This represents an attack surface for indirect prompt injection, where malicious instructions could be embedded in the retrieved news.
Ingestion points: External news articles and market data retrieved by the specified tools in SKILL.md.
Boundary markers: None specified; the skill does not explicitly instruct the agent to use delimiters for external data.
Capability inventory: Limited to data retrieval and time-based summarization; the skill lacks dangerous capabilities such as file system writing or arbitrary network exfiltration.
Sanitization: No sanitization or filtering logic is defined for the ingested content.
[SAFE]: The skill uses platform-provided tools for its primary purpose of news summarization. The YAML configuration restricts execution by disabling implicit invocation and model-led invocation, which are positive security constraints.

stock-news