design-content-script

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of instructional markdown that defines a narrative design process. It contains no executable scripts, shell commands, or network operations.
  • [INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read from local reference files (references/design-best-practices.md, references/design-inspiration-catalog.md, DESIGN.md) to inform the design output. While this constitutes a data ingestion surface, the skill lacks the capabilities (such as network access or code execution) required to exploit such an injection.
  • Ingestion points: Reads from local project markdown files in the references/ directory and the project root.
  • Boundary markers: The skill uses a structured output template for 02-design.md, which helps maintain separation between ingested content and the resulting analysis.
  • Capability inventory: The skill is limited to reading and writing local markdown documents.
  • Sanitization: No specific sanitization is implemented, but the restricted tool environment makes this a safe interaction.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 06:47 AM
Security Audit — agent-trust-hub — design-content-script