midjourney-card-news-backgrounds

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • NO_CODE (SAFE): The skill consists entirely of Markdown instructions and documentation. There are no scripts (.py, .js, .sh), configuration files for package managers, or executable binaries included in the analyzed files.
  • DATA_EXFILTRATION (SAFE): No hardcoded credentials, API keys, or sensitive file paths (like .ssh or .aws) were detected. The skill does not perform any network operations (curl, wget, fetch).
  • INDIRECT_PROMPT_INJECTION (SAFE): While the skill processes user-supplied topics, it has a low risk profile as it only generates text prompts for image generation.
  • Ingestion points: User input via the 'topic' field in SKILL.md.
  • Boundary markers: The skill uses a structured prompt format [subject], [style], [color], [texture], [technical] which acts as a natural separator for user input.
  • Capability inventory: The skill only outputs text. It lacks any capabilities to execute commands, write files, or access the network.
  • Sanitization: The instructions explicitly tell the agent to 'Extract the main subject', which serves to filter out non-subject instructions embedded in user input.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:10 PM