navigation-design

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [NO_CODE]: The skill is composed exclusively of documentation in Markdown format and a license file. It does not include any executable scripts, binaries, or automated tool configurations.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests external data sources such as navigation registries and screenshots, which are potential vectors for indirect prompt injection.
  • Ingestion points: SKILL.md (instructions to load authority baselines and process screenshots).
  • Boundary markers: Not specified.
  • Capability inventory: None (no code or tool access).
  • Sanitization: None specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 06:50 AM