navigation-menu-generator
Pass
Audited by Gen Agent Trust Hub on Aug 26, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed entirely of design principles and checklists for website navigation structures and does not include any executable code or remote script downloads.- [INDIRECT_PROMPT_INJECTION]: The skill identifies and reads local project context files (".claude/project-context.md" or ".cursor/project-context.md") to tailor its design recommendations. While this represents a data ingestion surface, the risk is minimal as the skill's capabilities are restricted to generating documentation.
- Ingestion points: Context files are accessed during the "Initial Assessment" phase defined in "SKILL.md".
- Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present.
- Capability inventory: The skill provides text-based design advice and lacks access to tools for network communication, system configuration, or file modification.
- Sanitization: The skill does not perform validation or filtering of the ingested content.
Audit Metadata