The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted external data from web searches and news sources during its 'Tracking Check' mode, which introduces a surface for indirect prompt injection. A maliciously crafted news article or financial report could attempt to influence the agent's evaluation of thesis health or sell conditions.
Ingestion points: Data enters the agent's context through web_search, get_stock_news, and get_financial_statements.
Boundary markers: The instructions lack explicit delimiters or guidance for the agent to distinguish between its internal logic and potentially instructional content within the external data.
Capability inventory: The agent has the ability to read and write files (read_file, write_file) in the reports/ directory based on tool outputs.
Sanitization: There is no evidence of sanitization, validation, or filtering of the content retrieved from external sources before it is processed.

thesis-tracker