aesthetic-application

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from user-specified local files and external tool outputs, creating a surface for indirect prompt injection.
  • Ingestion points: The skill loads files from the local filesystem (knowledge/aesthetics/<slug>.md) and incorporates output from the image-analysis skill into its prompts.
  • Boundary markers: The instructions do not define clear delimiters or use 'ignore embedded instructions' warnings for the data ingested from aesthetic profiles or image analysis.
  • Capability inventory: The skill possesses file-reading capabilities to access and load data from its knowledge base.
  • Sanitization: No validation or sanitization logic is specified for the aesthetic identifier (slug) or the content of the ingested data files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 07:34 PM
Security Audit — agent-trust-hub — aesthetic-application