build-resource-pages

Pass

Audited by Gen Agent Trust Hub on Apr 3, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection because it ingests untrusted markdown data to generate production-ready code. * Ingestion points: Markdown files located in workspace/[brand]/content/resources/ and the content_architecture.md file. * Boundary markers: The skill instructions do not specify any delimiters or warnings to ignore embedded instructions within the source markdown files. * Capability inventory: The skill has the capability to read local files, discover the project structure via shell commands, and write significant amounts of frontend code to the repository. * Sanitization: No mention is made of sanitizing or validating the markdown body for malicious instructions before using it to influence code generation.
  • [COMMAND_EXECUTION]: The Phase 1 discovery workflow requires the agent to execute shell commands to identify the framework, styling tokens, and routing patterns of the client codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 3, 2026, 02:42 PM