seatmaps

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the agent-browser utility from the public npm registry.
  • [COMMAND_EXECUTION]: The skill utilizes the agent-browser CLI to perform web automation tasks, such as navigating to specific URLs, filling search forms, and capturing snapshots of external content. These operations are explicitly scoped within the allowed-tools section of the manifest.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core function of fetching and processing content from external websites.
  • Ingestion points: Data is ingested from seatmaps.com and aerolopa.com via the agent-browser snapshot -c command in SKILL.md.
  • Boundary markers: The instructions do not define delimiters or provide specific warnings to the agent to disregard potential instructions or malicious patterns found within the fetched web content.
  • Capability inventory: The skill is authorized to use agent-browser for browser automation, which includes interacting with forms and extracting page content.
  • Sanitization: There is no evidence of data sanitization or validation being performed on the content retrieved from external sources before it is interpreted by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 11:25 AM
Security Audit — agent-trust-hub — seatmaps