annual-dividend

Pass

Audited by Gen Agent Trust Hub on Oct 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external website (Yahoo Finance) via the chrome-devtools tool and processes it to generate tables and notes. It does not implement sanitization or boundary markers to prevent the agent from accidentally executing instructions that might be embedded in the scraped content.
  • Ingestion points: Scrapes column headers, row labels, and dividend values from the Yahoo Finance financials page (e.g., div.tableBody div.row) using the evaluate_script tool as described in Step 3 of SKILL.md.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the scraped table data.
  • Capability inventory: The skill has access to powerful tools including Task (for spawning parallel subagents), Bash, Grep, and a full suite of chrome-devtools functions.
  • Sanitization: No data validation, escaping, or filtering is applied to the scraped strings before they are incorporated into the agent's final markdown output or the notes section.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 4, 2026, 03:07 PM