404-page-generator

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external project context files located at .claude/project-context.md or .cursor/project-context.md to inform its design and brand suggestions.
  • Ingestion points: Specifically reads local project-level markdown files for brand voice, key pages, and visual identity sections.
  • Boundary markers: No specific delimiters or explicit instructions to ignore embedded commands within the context files are defined.
  • Capability inventory: The skill is restricted to text generation (copy, link structures, and checklists) and does not possess capabilities for network operations, file system modifications, or command execution.
  • Sanitization: There is no evidence of sanitization or filtering applied to the content retrieved from these context files, although the risk is minimal given the skill's limited text-only output capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 07:25 AM