get-started

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data provided by the user, including URLs, content drafts, and data exports.
  • Ingestion points: User-provided URLs, text drafts, and file exports (SKILL.md).
  • Boundary markers: The instructions explicitly state that no account, payment, or contact information is required for these workflows (SKILL.md).
  • Capability inventory: The skill makes use of platform-provided browsing, file, and execution tools (SKILL.md).
  • Sanitization: The instructions do not specify explicit sanitization or escaping of the ingested external content.
  • [EXTERNAL_DOWNLOADS]: The workflow involves using browsing tools to access and analyze content from external URLs provided by the user.
  • [COMMAND_EXECUTION]: The skill instructions mention using available "execution tools" for diagnostic purposes and handling files, directed to be done within the context of the installed plugin root.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 01:29 PM