skills/proxy2021/enso/photobook/Gen Agent Trust Hub

photobook

Pass

Audited by Gen Agent Trust Hub on Oct 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of tool definitions for a photobook application. It does not include any executable code, scripts, or suspicious instructions in the manifest.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads file system information and processes user-supplied text to create photobooks.
  • Ingestion points: Parameters path in enso_photobook_browse, photoPaths in enso_photobook_create, and textUpdates in enso_photobook_edit (SKILL.md).
  • Boundary markers: None identified; there are no instructions to the agent to distinguish between data and potential commands.
  • Capability inventory: The skill provides capabilities for directory listing and exporting content to PDF or images.
  • Sanitization: No input validation or sanitization procedures are specified in the tool manifest.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 1, 2026, 02:09 AM