acid-depth-poster

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of Markdown instructions and reference templates. It does not contain any executable scripts (Python, JavaScript, etc.) or binary files.
  • [SAFE]: The primary purpose is to transform user-provided themes into structured text prompts for image models. The workflow uses a 'master-template' to maintain stylistic consistency.
  • [DATA_EXPOSURE]: No sensitive file paths, environment variables, or hardcoded credentials were detected. The network operations are limited to the agent's internal referencing of local files within the skill folder.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests user input (themes, titles) and interpolates it into a prompt template. While this is a common surface for prompt injection, the risk is assessed as safe because the output is intended for the user to manually copy into an image generation tool, providing a human-in-the-loop checkpoint. The instructions explicitly warn against including 'meaningless text' or 'decorative pattern overload'.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 04:12 AM
Security Audit — agent-trust-hub — acid-depth-poster