use-tinyfish

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes the tinyfish command-line utility to perform browser automation tasks and data scraping based on natural language instructions.
  • [EXTERNAL_DOWNLOADS]: Requires the installation of the @tiny-fish/cli package from the NPM registry, which is the official tool provided by the vendor.
  • [PROMPT_INJECTION]: The skill processes content from external websites, which presents a surface for indirect prompt injection where instructions on a webpage could attempt to influence agent actions.
  • Ingestion points: Website content accessed via the --url flag in the tinyfish agent run command.
  • Boundary markers: No specific boundary markers or instructions are provided to distinguish between user goals and retrieved web data.
  • Capability inventory: The tinyfish CLI provides full browser automation capabilities including navigation, clicking, and form interaction.
  • Sanitization: No explicit sanitization or filtering of the scraped content is described in the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 06:32 PM