google-flights

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes agent-browser commands via Bash to automate flight searches. It interpolates user-provided variables like {ORIGIN} and {DEST} directly into shell command strings, which creates a surface for potential command injection if input is not validated by the agent.- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the agent-browser package from the npm registry as a prerequisite for its browser automation functionality.- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface due to its interaction with external web content.
  • Ingestion points: Flight descriptions and booking data are retrieved from Google Flights via the agent-browser snapshot command in SKILL.md.
  • Boundary markers: The skill lacks explicit delimiters or instructions to the agent to ignore potentially malicious instructions embedded in the external flight data.
  • Capability inventory: The skill uses the Bash tool to execute browser automation and process results.
  • Sanitization: No content sanitization or input validation is specified before the agent processes the retrieved data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 11:09 AM
Security Audit — agent-trust-hub — google-flights