google-flights

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external search results on Google Flights, which serves as an ingestion point for untrusted content that could influence agent behavior.
  • Ingestion points: Browser snapshots captured from google.com/travel/flights (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters or "ignore embedded instructions" warnings for the processed flight data.
  • Capability inventory: The agent possesses capabilities to execute browser automation commands, navigate URLs, and perform clicks through agent-browser (SKILL.md).
  • Sanitization: There is no evidence of sanitization or validation of the extracted flight descriptions before they are parsed into markdown tables.
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the agent-browser CLI tool from the npm registry and execute its internal installation command to set up the browser environment.
  • [COMMAND_EXECUTION]: The skill makes extensive use of the Bash tool to execute agent-browser commands for managing sessions, navigating to dynamically constructed URLs, interacting with page elements (e.g., clicking results), and generating snapshots.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 02:01 PM