skills/berkay-digital/skills/facehash/Gen Agent Trust Hub

facehash

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (MEDIUM): The skill recommends installing the facehash package via npm/yarn. Since facehash is not from a predefined trusted organization, it is considered an unverifiable dependency. However, this is the primary purpose of the skill, resulting in a downgrade to LOW.
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection through data processing.
  • Ingestion points: The name property of the <Facehash /> component (SKILL.md).
  • Boundary markers: Absent; no delimiters or warnings for the agent to ignore instructions embedded in the name string are provided.
  • Capability inventory: Limited to UI rendering and React/Next.js component usage; no file-system, subprocess, or network capabilities are demonstrated in the snippets.
  • Sanitization: Absent; the usage examples do not show input validation or sanitization for the name string before it is processed by the library.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:49 PM