quarterly-eps
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from an external web source (Yahoo Finance) which introduces a potential attack surface where malicious content on the page could influence agent behavior.
- Ingestion points: External data is ingested via
mcp__chrome-devtools__take_snapshotandevaluate_scriptinSKILL.md(Step 2 and 3). - Boundary markers: The instructions lack explicit delimiters or instructions to ignore potential commands embedded in the scraped financial data.
- Capability inventory: The skill uses high-privilege tools including
Bash,Task(for agent orchestration), and various Chrome DevTools commands. - Sanitization: There is no evidence of sanitization or validation of the text extracted from the web page before it is processed into the final markdown tables.
Audit Metadata