vertical-creator

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The core logic of the skill involves creating and validating declarative configuration files (JSON) and markdown templates for a development framework. The instructions promote good practices such as validation and testing. The use of the ha CLI tool is consistent with the skill's stated purpose and does not involve suspicious network or system operations.- [PROMPT_INJECTION]: The skill processes external configuration files and markdown templates, creating a surface for indirect prompt injection where malicious instructions could be embedded in the data the skill reviews or materializes.
  • Ingestion points: Reads and updates vertical definitions, template catalogs, and markdown assets as specified in the workflow in SKILL.md.
  • Boundary markers: The instructions lack explicit directives for the agent to use delimiters or treat the content of these files as untrusted data.
  • Capability inventory: The agent is tasked with executing the ha CLI for validation and materializing templates to the filesystem.
  • Sanitization: No specific content sanitization or instruction filtering is implemented for the data found within vertical assets.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 05:09 AM
Security Audit — agent-trust-hub — vertical-creator