The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources such as web searches and company filings, which could potentially contain malicious instructions designed to influence the agent's behavior during report generation.
Ingestion points: External data is ingested via WebSearch for news headlines and catalysts, and through keyword searches of recent filings.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' prompts when processing retrieved external text.
Capability inventory: The skill has the capability to write files to the local filesystem (reports/{TICKER}_tearsheet.html).
Sanitization: There are no explicit sanitization or filtering steps mentioned for the content retrieved from external searches before it is included in the final report.
[EXTERNAL_DOWNLOADS]: The skill performs web searches using WebSearch to gather current news and event data from the internet.
[COMMAND_EXECUTION]: The skill instructs the agent to write a structured HTML report to the local reports/ directory based on the collected financial and news data.

tearsheet