quarterly-revenue
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied ticker symbols and interpolates them directly into subagent task descriptions and web navigation URLs.
- Ingestion points: The $0 argument in SKILL.md (list of tickers).
- Boundary markers: Absent; user input is not delimited or wrapped in instructions to prevent the agent from following instructions embedded within ticker strings.
- Capability inventory: The skill uses the Task tool to launch subagents, Bash for local command execution (Grep), and Chrome DevTools for web interaction and script evaluation.
- Sanitization: Absent; the skill does not validate or sanitize ticker symbols before interpolation.
- [EXTERNAL_DOWNLOADS]: Fetches financial data from Yahoo Finance, which is a well-known and expected service for this functionality.
- [COMMAND_EXECUTION]: Uses Bash and Grep to process large snapshots of web pages locally. This is standard behavior for managing scraping results.
Audit Metadata